1,564
个编辑
更改
跳到导航
跳到搜索
小第1行：
第1行： − 此词条暂由彩云小译翻译，未经人工整理和审校，带来阅读不便，请见谅。+ − '''Swarm intelligence''' ('''SI''') is the [[collective behavior]] of [[decentralization|decentralized]], [[Self-organization|self-organized]] systems, natural or artificial. The concept is employed in work on [[artificial intelligence]]. The expression was introduced by [[Gerardo Beni]] and Jing Wang in 1989, in the context of cellular robotic systems.<ref>{{cite book|author=Beni, G., Wang, J.|chapter=Swarm Intelligence in Cellular Robotic Systems|title=Proceed. NATO Advanced Workshop on Robots and Biological Systems, Tuscany, Italy, June 26–30 (1989)|pages=703–712|doi=10.1007/978-3-642-58069-7_38|year=1993|isbn=978-3-642-63461-1}}</ref>+ − + − 群体智能是分散的、自组织的系统的集体行为，无论是自然的还是人为的。这个概念被应用于人工智能领域。这个表达是由 Gerardo Beni 和 Jing Wang 在1989年在蜂窝机器人系统中引入的。+ + + 第11行：
第13行： − SI systems consist typically of a population of simple agents or boids interacting locally with one another and with their environment. The inspiration often comes from nature, especially biological systems. The agents follow very simple rules, and although there is no centralized control structure dictating how individual agents should behave, local, and to a certain degree random, interactions between such agents lead to the emergence of "intelligent" global behavior, unknown to the individual agents. Examples of swarm intelligence in natural systems include ant colonies, bird flocking, hawks hunting, animal herding, bacterial growth, fish schooling and microbial intelligence. − Si 系统通常由一群简单的代理程序或 boids 组成，这些代理程序或 boids 在本地相互作用，并与它们的环境相互作用。灵感往往来自大自然，尤其是生物系统。代理遵循非常简单的规则，虽然没有集中的控制结构规定个体代理应该如何行动，局部的，在一定程度上是随机的，这些代理之间的相互作用导致出现“智能”全局行为，个体代理不知道。自然系统中的群体智能包括蚁群、鸟群、鹰狩猎、动物群居、细菌生长、鱼群和微生物智能。 + + − + − The application of swarm principles to robots is called swarm robotics, while 'swarm intelligence' refers to the more general set of algorithms. 'Swarm prediction' has been used in the context of forecasting problems. Similar approaches to those proposed for swarm robotics are considered for genetically modified organisms in synthetic collective intelligence. − 将群体原理应用于机器人被称为群体机器人学，而群体智能机器人学则是指一组更为一般的算法。“群体预测”一直被用于预测问题。类似的方法被提议用于群体机器人技术，在合成的集体智慧中被考虑用于基因改造的有机体。 + + 第36行：
第38行： − − Boids is an artificial life program, developed by Craig Reynolds in 1986, which simulates the flocking behaviour of birds. His paper on this topic was published in 1987 in the proceedings of the ACM SIGGRAPH conference.<ref name = reynolds>{{Cite book − − Boids 是一个人工生命程序，由克雷格 · 雷诺兹于1986年开发，模拟鸟类的群集行为。他关于这个主题的论文发表在1987年的 ACM SIGGRAPH 会议记录上。 1.1.1.1.1.2.1.2.2.1.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2.2 − − | last1=Reynolds − − 最后1雷诺 − + − − 第一名: 克雷格 − − | author1-link=Craig Reynolds (computer_graphics) − − | author1-link Craig Reynolds (计算机图形学) − − | title=Flocks, herds and schools: A distributed behavioral model. − − 羊群、畜群和学校: 一个分布式的行为模型。 − − | year=1987 − − 1987年 − − | volume= − − 音量 − − | number= − − 数字 − − | journal=SIGGRAPH '87: Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques − − 87: 第14届计算机图形学与互动技术年度会议论文集 − − | publisher=Association for Computing Machinery − − | 出版商计算机协会 − − | pages=25–34 − − 第25-34页 − − | isbn=978-0-89791-227-3 − − [国际标准图书编号978-0-89791-227-3] − − | doi=10.1145/37401.37406 − − 10.1145 / 37401.37406 − − | citeseerx=10.1.1.103.7187 − − 10.1.1.103.7187 − − }}</ref> − − } / ref − − The name "boid" corresponds to a shortened version of "bird-oid object", which refers to a bird-like object.<ref>{{Cite journal − − 名称“ boid”对应于一个缩短版的“ bird-oid object” ，它指的是一个类似鸟的对象 − − | last1=Banks − − 1 Banks − − | first1=Alec − − 首先 Alec − − | last2=Vincent − − 最后2文森特 − − | first2=Jonathan − − 第二名: 乔纳森 − − | last3=Anyakoha − − 3 / lastanyakoha − − | first3=Chukwudi − | first3 Chukwudi+ − − − − 2012年10月12日 | 标题: 粒子群优化的回顾。第一部分: 背景与发展 − − |date=July 2007 − − 2007年7月 − − | volume=6 − − 第六卷 − − | issue=4 − − 第四期 − − | pages=467–484 − − 第467-484页 − − | journal=Natural Computing − − 自然计算杂志 − − | doi=10.1007/s11047-007-9049-5 − − 10.1007 / s11047-007-9049-5 − − | citeseerx=10.1.1.605.5879 − − 10.1.1.605.5879 − − }}</ref> − − {} / ref − − As with most artificial life simulations, Boids is an example of emergent behavior; that is, the complexity of Boids arises from the interaction of individual agents (the boids, in this case) adhering to a set of simple rules. The rules applied in the simplest Boids world are as follows: − − 与大多数人工生命模拟一样，Boids 是突发行为的一个例子; 也就是说，Boids 的复杂性来自于个体代理(这里是 Boids)遵循一系列简单规则的相互作用。在最简单的博伊德世界中适用的规则如下: 第242行：
第120行： − − More complex rules can be added, such as obstacle avoidance and goal seeking. − − 可以添加更复杂的规则，如避障和寻找目标。 第253行：
第127行： − + − − Self-propelled particles (SPP), also referred to as the Vicsek model, was introduced in 1995 by Vicsek et al. as a special case of the boids model introduced in 1986 by Reynolds. SPP models predict that swarming animals share certain properties at the group level, regardless of the type of animals in the swarm. Swarming systems give rise to emergent behaviours which occur at many different scales, some of which are turning out to be both universal and robust. It has become a challenge in theoretical physics to find minimal statistical models that capture these behaviours. − − 自推进粒子(SPP) ，也称为维塞克模型，是在1995年由维塞克等人介绍。作为雷诺兹于1986年提出的 boids 模型的一个特例。Spp 模型预测，群集动物在群体水平上具有某些特性，而不管群集中的动物是什么类型。群集系统产生在许多不同尺度下出现的突发行为，其中一些已被证明是普遍的和健壮的。找到能够捕捉这些行为的最小统计模型已经成为理论物理学的一个挑战。 第265行：
第135行： − + + − Evolutionary algorithms (EA), particle swarm optimization (PSO), differential evolution (DE), ant colony optimization (ACO) and their variants dominate the field of nature-inspired metaheuristics. This list includes algorithms published up to circa the year 2000. A large number of more recent metaphor-inspired metaheuristics have started to attract criticism in the research community for hiding their lack of novelty behind an elaborate metaphor. For algorithms published since that time, see List of metaphor-based metaheuristics. − 进化算法(EA)、粒子群优化算法(PSO)、差异进化算法算法(DE)、蚁群优化算法(ACO)及其变体在启发自然的元启发式算法领域占据主导地位。这份清单包括了大约在2000年前后发表的算法。大量最近受隐喻启发的启发式元推理已经开始在研究界引起批评，因为它们把缺乏新颖性隐藏在一个精心设计的隐喻后面。有关那时以来发表的算法，请参阅基于隐喻的启发式列表。+ 第277行：
第147行： − + − − First published in 1989 Stochastic diffusion search (SDS) was the first Swarm Intelligence metaheuristic. SDS is an agent-based probabilistic global search and optimization technique best suited to problems where the objective function can be decomposed into multiple independent partial-functions. Each agent maintains a hypothesis which is iteratively tested by evaluating a randomly selected partial objective function parameterised by the agent's current hypothesis. In the standard version of SDS such partial function evaluations are binary, resulting in each agent becoming active or inactive. Information on hypotheses is diffused across the population via inter-agent communication. Unlike the stigmergic communication used in ACO, in SDS agents communicate hypotheses via a one-to-one communication strategy analogous to the tandem running procedure observed in Leptothorax acervorum. A positive feedback mechanism ensures that, over time, a population of agents stabilise around the global-best solution. SDS is both an efficient and robust global search and optimisation algorithm, which has been extensively mathematically described. Recent work has involved merging the global search properties of SDS with other swarm intelligence algorithms. − − 首次发表于1989年的随机扩散搜索是第一个群体智能元启发式搜索。Sds 是一种基于代理的概率全局搜索和优化技术，最适合于将目标函数分解为多个独立部分函数的问题。每个主体维持一个假设，这个假设通过评估一个随机选择的部分目标函数迭代检验，该目标函数由主体的当前假设参数化。在 SDS 的标准版本中，这样的部分功能评估是二进制的，导致每个代理变得活跃或不活跃。关于假说的信息通过代理人之间的交流在人群中传播。与蚁群优化算法不同的是，SDS 代理通过一对一的交流策略进行假设交流，这种交流策略类似于 Leptothorax acervorum 中观察到的串联跑步过程。一个积极的反馈机制可以确保，随着时间的推移，围绕这个全球最佳解决方案的代理人群逐渐稳定下来。Sds 是一种高效、健壮的全局搜索和优化算法，已经在数学上得到了广泛的描述。最近的工作包括合并 SDS 的全局搜索属性和其他群体智能算法。 第290行：
第156行： − − Ant colony optimization (ACO), introduced by Dorigo in his doctoral dissertation, is a class of optimization algorithms modeled on the actions of an ant colony. ACO is a probabilistic technique useful in problems that deal with finding better paths through graphs. Artificial 'ants'—simulation agents—locate optimal solutions by moving through a parameter space representing all possible solutions. Natural ants lay down pheromones directing each other to resources while exploring their environment. The simulated 'ants' similarly record their positions and the quality of their solutions, so that in later simulation iterations more ants locate for better solutions. − − 蚁群优化是 Dorigo 在他的《博士论文引入的一类基于蚁群行为的优化算法。蚁群算法是一种概率技术，用于处理通过图寻找更好的路径的问题。人工“蚂蚁”ーー模拟代理ーー通过移动代表所有可能解的参数空间来确定最优解。自然界的蚂蚁在探索自己的环境时，会产生信息素，互相引导对方寻找资源。模拟的“蚂蚁”类似地记录它们的位置和解决方案的质量，这样在随后的模拟迭代中更多的蚂蚁找到更好的解决方案。 第301行：
第163行： − + − − Particle swarm optimization (PSO) is a global optimization algorithm for dealing with problems in which a best solution can be represented as a point or surface in an n-dimensional space. Hypotheses are plotted in this space and seeded with an initial velocity, as well as a communication channel between the particles. Particles then move through the solution space, and are evaluated according to some fitness criterion after each timestep. Over time, particles are accelerated towards those particles within their communication grouping which have better fitness values. The main advantage of such an approach over other global minimization strategies such as simulated annealing is that the large number of members that make up the particle swarm make the technique impressively resilient to the problem of local minima. − − 粒子群优化优化算法是一种全局优化算法，用于处理一个最优解可以表示为 n 维空间中的一个点或表面的问题。在这个空间中绘制假设，并以初始速度播种，以及粒子之间的通信通道。然后粒子穿过解空间，在每个时间步后根据一定的适应度准则进行评价。随着时间的推移，粒子被加速到它们通信分组中具有更好的适应值的那些粒子。这种方法相对于其他全局最小化策略的主要优势在于组成粒子群的大量成员使得这种技术对局部极小问题具有令人印象深刻的弹性。比如模拟退火。 第311行：
第169行： − + − − Artificial Swarm Intelligence (ASI) is method of amplifying the collective intelligence of networked human groups using control algorithms modeled after natural swarms. Sometimes referred to as Human Swarming or Swarm AI, the technology connects groups of human participants into real-time systems that deliberate and converge on solutions as dynamic swarms when simultaneously presented with a question ASI has been used for a wide range of applications, from enabling business teams to generate highly accurate financial forecasts to enabling sports fans to outperform Vegas betting markets. ASI has also been used to enable groups of doctors to generate diagnoses with significantly higher accuracy than traditional methods. − − 人工群体智能是一种利用模仿自然蜂群的控制算法来增强网络化人类群体的集体智慧的方法。这种技术有时被称为“人类群集”(Human Swarming)或“ Swarm AI”(Swarm AI) ，它将人类参与者群体连接到实时系统中，当 ASI 同时提出一个问题时，这些实时系统将作为动态群集的解决方案进行深思熟虑并聚合在一起。 ASI 已被广泛应用于各种应用中，从使商业团队能够产生高度精确的财务预测，到使体育迷们能够超越拉斯维加斯的博彩市场。意大利空间局还被用于使医生群体能够以比传统方法高得多的准确度进行诊断。 第321行：
第175行： − + − − Swarm Intelligence-based techniques can be used in a number of applications. The U.S. military is investigating swarm techniques for controlling unmanned vehicles. The European Space Agency is thinking about an orbital swarm for self-assembly and interferometry. NASA is investigating the use of swarm technology for planetary mapping. A 1992 paper by M. Anthony Lewis and George A. Bekey discusses the possibility of using swarm intelligence to control nanobots within the body for the purpose of killing cancer tumors. Conversely al-Rifaie and Aber have used stochastic diffusion search to help locate tumours. Swarm intelligence has also been applied for data mining. Ant based models are further subject of modern management theory. − − 基于群体智能的技术可以应用于许多领域。美国军方正在研究用于控制无人驾驶飞行器的群技术。欧洲航天局正在考虑一个用于自组装和干涉测量的轨道群。美国宇航局正在研究群体技术在行星测绘中的应用。和 George a. Bekey 在1992年的一篇论文中讨论了使用群体智能控制人体内的纳米机器人以杀死癌症肿瘤的可能性。相反，al-Rifaie 和 Aber 使用随机扩散搜索帮助定位肿瘤。群体智能也应用于数据挖掘。基于蚁群算法的模型是现代管理理论的进一步研究课题。 − − ===Ant-based routing=== − − The use of swarm intelligence in [[Telecommunications network|telecommunication networks]] has also been researched, in the form of [[Ant colony optimization algorithms|ant-based routing]]. This was pioneered separately by Dorigo et al. and [[Hewlett Packard]] in the mid-1990s, with a number of variants existing. Basically, this uses a [[Probabilistic algorithm|probabilistic]] routing table rewarding/reinforcing the route successfully traversed by each "ant" (a small control packet) which flood the network. Reinforcement of the route in the forwards, reverse direction and both simultaneously have been researched: backwards reinforcement requires a symmetric network and couples the two directions together; forwards reinforcement rewards a route before the outcome is known (but then one would pay for the cinema before one knows how good the film is). As the system behaves stochastically and is therefore lacking repeatability, there are large hurdles to commercial deployment. Mobile media and new technologies have the potential to change the threshold for collective action due to swarm intelligence (Rheingold: 2002, P175). − − The use of swarm intelligence in telecommunication networks has also been researched, in the form of ant-based routing. This was pioneered separately by Dorigo et al. and Hewlett Packard in the mid-1990s, with a number of variants existing. Basically, this uses a probabilistic routing table rewarding/reinforcing the route successfully traversed by each "ant" (a small control packet) which flood the network. Reinforcement of the route in the forwards, reverse direction and both simultaneously have been researched: backwards reinforcement requires a symmetric network and couples the two directions together; forwards reinforcement rewards a route before the outcome is known (but then one would pay for the cinema before one knows how good the film is). As the system behaves stochastically and is therefore lacking repeatability, there are large hurdles to commercial deployment. Mobile media and new technologies have the potential to change the threshold for collective action due to swarm intelligence (Rheingold: 2002, P175). − − 群体智能在电信网络中的应用也被研究过，采用基于蚂蚁的路由方式。这是由 Dorigo 等人单独开创的。和惠普在1990年代中期，与一些变种存在。基本上，这使用了一个概率路由表来奖励 / 增强每个“蚂蚁”(一个小的控制包)成功通过的路由，这些“蚂蚁”遍布整个网络。前进路线、反向路线以及两者同时被研究: 后退路线需要一个对称的网络并将两个方向连接在一起; 前进路线在结果知道之前奖励一条路线(但是在人们知道电影有多好之前，他们就会为电影付钱)。由于该系统的随机行为，因此缺乏可重复性，商业部署有很大的障碍。移动媒体和新技术有可能改变群体智能集体行动的门槛。 − − − − The location of transmission infrastructure for wireless communication networks is an important engineering problem involving competing objectives. A minimal selection of locations (or sites) are required subject to providing adequate area coverage for users. A very different-ant inspired swarm intelligence algorithm, stochastic diffusion search (SDS), has been successfully used to provide a general model for this problem, related to circle packing and set covering. It has been shown that the SDS can be applied to identify suitable solutions even for large problem instances.<ref>Whitaker, R.M., Hurley, S.. [https://dl.acm.org/citation.cfm?id=508902 An agent based approach to site selection for wireless networks]. Proc ACM Symposium on Applied Computing, pp. 574–577, (2002).</ref> − − The location of transmission infrastructure for wireless communication networks is an important engineering problem involving competing objectives. A minimal selection of locations (or sites) are required subject to providing adequate area coverage for users. A very different-ant inspired swarm intelligence algorithm, stochastic diffusion search (SDS), has been successfully used to provide a general model for this problem, related to circle packing and set covering. It has been shown that the SDS can be applied to identify suitable solutions even for large problem instances. − − 无线通信网络传输基础设施的选址问题是一个涉及竞争对象的重要工程问题。在为用户提供足够覆盖面积的前提下，需要选择最少的地点(或地点)。一个非常不同的蚂蚁启发的群体智能搜索算法，随机扩散搜索(SDS) ，已经被成功地用来为这个问题提供一个通用模型，与圆填充和集合覆盖有关。已经表明，即使对于大的问题实例，SDS 也可以用来确定合适的解决方案。 − − − − Airlines have also used ant-based routing in assigning aircraft arrivals to airport gates. At [[Southwest Airlines]] a software program uses swarm theory, or swarm intelligence—the idea that a colony of ants works better than one alone. Each pilot acts like an ant searching for the best airport gate. "The pilot learns from his experience what's the best for him, and it turns out that that's the best solution for the airline," [[Douglas A. Lawson]] explains. As a result, the "colony" of pilots always go to gates they can arrive at and depart from quickly. The program can even alert a pilot of plane back-ups before they happen. "We can anticipate that it's going to happen, so we'll have a gate available," Lawson says.<ref>{{cite news |work=Science Daily |date=April 1, 2008 |title=Planes, Trains and Ant Hills: Computer scientists simulate activity of ants to reduce airline delays |url=https://www.sciencedaily.com/videos/2008/0406-planes_trains_and_ant_hills.htm |access-date=December 1, 2010 |url-status=dead |archive-url=https://web.archive.org/web/20101124132227/https://www.sciencedaily.com/videos/2008/0406-planes_trains_and_ant_hills.htm |archive-date=November 24, 2010 }}</ref> − − Airlines have also used ant-based routing in assigning aircraft arrivals to airport gates. At Southwest Airlines a software program uses swarm theory, or swarm intelligence—the idea that a colony of ants works better than one alone. Each pilot acts like an ant searching for the best airport gate. "The pilot learns from his experience what's the best for him, and it turns out that that's the best solution for the airline," Douglas A. Lawson explains. As a result, the "colony" of pilots always go to gates they can arrive at and depart from quickly. The program can even alert a pilot of plane back-ups before they happen. "We can anticipate that it's going to happen, so we'll have a gate available," Lawson says. − − 航空公司也使用基于蚂蚁的路由分配飞机到达机场登机口。西南航空公司(Southwest Airlines)的一个软件程序使用了群体理论(swarm intelligence，简称群体智能)——群体智能认为一群蚂蚁比单独一个蚂蚁更有效。每个飞行员都像蚂蚁一样寻找最好的机场大门。道格拉斯 · a · 劳森解释说: “飞行员从自己的经历中学到了什么对他来说是最好的，结果证明这是航空公司的最佳解决方案。”。因此，飞行员的“群体”总是走向他们能够快速到达和离开的大门。该程序甚至可以在飞机备份发生之前通知飞行员。劳森说: “我们可以预见到这种情况会发生，所以我们有一个可用的登机口。”。 − − − − ===Crowd simulation=== − − Artists are using swarm technology as a means of creating complex interactive systems or [[Crowd simulation|simulating crowds]]. − − Artists are using swarm technology as a means of creating complex interactive systems or simulating crowds. − − 艺术家们正在利用群技术创造复杂的交互系统或者模拟人群。 − − − − ''[[Stanley and Stella in: Breaking the Ice]]'' was the first movie to make use of swarm technology for rendering, realistically depicting the movements of groups of fish and birds using the Boids system. Tim Burton's ''[[Batman Returns]]'' also made use of swarm technology for showing the movements of a group of bats. [[The Lord of the Rings (film series)|''The Lord of the Rings'' film trilogy]] made use of similar technology, known as [[Massive (software)|Massive]], during battle scenes. Swarm technology is particularly attractive because it is cheap, robust, and simple. − − Stanley and Stella in: Breaking the Ice was the first movie to make use of swarm technology for rendering, realistically depicting the movements of groups of fish and birds using the Boids system. Tim Burton's Batman Returns also made use of swarm technology for showing the movements of a group of bats. The Lord of the Rings film trilogy made use of similar technology, known as Massive, during battle scenes. Swarm technology is particularly attractive because it is cheap, robust, and simple. − − 斯坦利和斯特拉在《破冰》中是第一部使用群体技术渲染的电影，利用博伊德系统逼真地描绘了鱼类和鸟类群体的动作。蒂姆 · 伯顿的《蝙蝠侠归来》也使用了群技术来显示一群蝙蝠的行动。《指环王》三部曲电影在战争场景中使用了类似的技术，被称为宏大。蜂群技术尤其具有吸引力，因为它廉价、健壮、简单。 − − − − Airlines have used swarm theory to simulate passengers boarding a plane. Southwest Airlines researcher Douglas A. Lawson used an ant-based computer simulation employing only six interaction rules to evaluate boarding times using various boarding methods.(Miller, 2010, xii-xviii).<ref>{{cite book |last=Miller |first=Peter |year=2010 |title=The Smart Swarm: How understanding flocks, schools, and colonies can make us better at communicating, decision making, and getting things done |publisher=Avery |location=New York |isbn=978-1-58333-390-7 |url-access=registration |url=https://archive.org/details/smartswarmhowund00mill }}</ref> − − Airlines have used swarm theory to simulate passengers boarding a plane. Southwest Airlines researcher Douglas A. Lawson used an ant-based computer simulation employing only six interaction rules to evaluate boarding times using various boarding methods.(Miller, 2010, xii-xviii). − − 航空公司已经使用群理论来模拟乘客登机。美国西南航空公司的研究员 Douglas a. Lawson 使用基于蚂蚁的计算机模拟程序，通过不同的登机方法，利用6个交互规则来计算登机时间。(米勒，2010，xii-xviii)。 − − − − ===Human swarming=== − − [[File:Human Swarm.gif|alt=Swarm AI system, answering a question in real-time|thumb|"Human Swarm" - this animated GIF shows a group of networked human participants, thinking together as a real-time system (i.e. a Hive Mind) moderated by swarming algorithms.]] − − "Human Swarm" - this animated GIF shows a group of networked human participants, thinking together as a real-time system (i.e. a Hive Mind) moderated by swarming algorithms. − − “人类群体”——这个动画 GIF 显示了一群网络化的人类参与者，他们一起作为一个实时系统思考(即。一个蜂群思维)由蜂群算法调节。 − − Enabled by mediating software such as the SWARM platform (formally unu) from [[Unanimous A.I.]], networks of distributed users can be organized into "human swarms" through the implementation of real-time closed-loop control systems.<ref>{{Cite web|url=http://www.bbc.com/future/story/20161215-why-bees-could-be-the-secret-to-superhuman-intelligence|title=Why bees could be the secret to superhuman intelligence|last=Oxenham|first=Simon|access-date=2017-01-20}}</ref><ref name="Inc.com">{{Cite news|url=https://www.inc.com/kevin-j-ryan/unanimous-ai-swarm-intelligence-makes-startlingly-accurate-predictions.html|title=This Startup Correctly Predicted the Oscars, World Series, and Super Bowl. Here's What It's Doing Next|date=2018-06-14|work=Inc.com|access-date=2018-09-10}}</ref><ref name="Rosenberg 58–62">{{Cite book|last=Rosenberg|first=L.|last2=Pescetelli|first2=N.|last3=Willcox|first3=G.|date=October 2017|title=Artificial Swarm Intelligence amplifies accuracy when predicting financial markets|journal=2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)|pages=58–62|doi=10.1109/UEMCON.2017.8248984|isbn=978-1-5386-1104-3|url=https://www.semanticscholar.org/paper/86b35476176e8dbc12bf05c00f8d8a0fa8194637}}</ref><ref name="Inc.com"/> As published by [[Louis B. Rosenberg|Rosenberg]] (2015), such real-time systems enable groups of human participants to behave as a unified [[collective intelligence]] that works as a single entity to make predictions, answer questions, and evoke opinions.<ref>http://sites.lsa.umich.edu/collectiveintelligence/wp-content/uploads/sites/176/2015/05/Rosenberg-CI-2015-Abstract.pdf</ref> Such systems, also referred to as "Artificial Swarm Intelligence" (or the brand name Swarm AI) have been shown to significantly amplify human intelligence,<ref>{{Cite journal|last=Metcalf|first=Lynn|last2=Askay|first2=David A.|last3=Rosenberg|first3=Louis B.|date=2019-07-17|title=Keeping Humans in the Loop: Pooling Knowledge through Artificial Swarm Intelligence to Improve Business Decision Making|journal=California Management Review|volume=61|issue=4|pages=84–109|doi=10.1177/0008125619862256|issn=0008-1256}}</ref><ref>{{Cite journal|last=Willcox|first=Gregg|last2=Rosenberg|first2=Louis|last3=Askay|first3=David|last4=Metcalf|first4=Lynn|last5=Harris|first5=Erick|last6=Domnauer|first6=Colin|date=2020|editor-last=Arai|editor-first=Kohei|editor2-last=Bhatia|editor2-first=Rahul|title=Artificial Swarming Shown to Amplify Accuracy of Group Decisions in Subjective Judgment Tasks|journal=Advances in Information and Communication|volume=70|series=Lecture Notes in Networks and Systems|language=en|publisher=Springer International Publishing|pages=373–383|doi=10.1007/978-3-030-12385-7_29|isbn=9783030123857}}</ref><ref name=":0">{{Cite journal|last=Rosenberg|first=Louis|last2=Willcox|first2=Gregg|date=2020|editor-last=Bi|editor-first=Yaxin|editor2-last=Bhatia|editor2-first=Rahul|editor3-last=Kapoor|editor3-first=Supriya|title=Artificial Swarm Intelligence|journal=Intelligent Systems and Applications|volume=1037|series=Advances in Intelligent Systems and Computing|language=en|publisher=Springer International Publishing|pages=1054–1070|doi=10.1007/978-3-030-29516-5_79|isbn=9783030295165}}</ref> resulting in a string of high-profile predictions of extreme accuracy.<ref>{{Cite news|url=http://www.newsweek.com/artificial-intelligence-turns-20-11000-kentucky-derby-bet-457783|title=Artificial intelligence turns $20 into $11,000 in Kentucky Derby bet|date=2016-05-10|newspaper=Newsweek|access-date=2017-01-20}}</ref><ref>{{Cite news|url=https://www.forbes.com/sites/janetwburns/2017/01/19/ai-that-clinched-the-trifecta-gave-the-super-bowl-to-green-bay-in-august/#679482212e74|title=AI That Clinched The Trifecta Gave The Super Bowl To Green Bay--In August|last=Burns|first=Janet|newspaper=Forbes|access-date=2017-01-20}}</ref><ref>{{cite web|url=https://mitpress.mit.edu/sites/default/files/titles/content/ecal2015/ch117.html|title=Human Swarms, a real-time method for collective intelligence|access-date=2015-10-12|archive-url=https://web.archive.org/web/20151027132802/https://mitpress.mit.edu/sites/default/files/titles/content/ecal2015/ch117.html|archive-date=2015-10-27|url-status=dead}}</ref><ref>{{cite web|url=http://news.discovery.com/human/life/swarms-of-humans-power-a-i-platform-150603.htm|title=Swarms of Humans Power A.I. Platform|work=DNews|date=2017-05-10}}</ref><ref name="Inc.com"/><ref name=":2">{{Cite news|url=https://www.techrepublic.com/article/how-ai-systems-beat-vegas-oddsmakers-in-sports-forecasting-accuracy/|title=How AI systems beat Vegas oddsmakers in sports forecasting accuracy|work=TechRepublic|access-date=2018-09-10}}</ref> Academic testing shows that human swarms can out-predict individuals across a variety of real-world projections.<ref>{{Cite book|last=Rosenberg|first=L.|last2=Baltaxe|first2=D.|last3=Pescetelli|first3=N.|date=2016-10-01|title=Crowds vs swarms, a comparison of intelligence|journal=2016 Swarm/Human Blended Intelligence Workshop (SHBI)|pages=1–4|doi=10.1109/SHBI.2016.7780278|isbn=978-1-5090-3502-1|url=https://www.semanticscholar.org/paper/af3ff5c83185c744c724242ec9ceaa3d9e952b9b}}</ref><ref>{{Cite book |doi = 10.1109/SHBI.2015.7321685|chapter = Human swarming, a real-time method for parallel distributed intelligence|title = 2015 Swarm/Human Blended Intelligence Workshop (SHBI)|pages = 1–7|year = 2015|last1 = Rosenberg|first1 = Louis B.|isbn = 978-1-4673-6522-2|chapter-url = https://www.semanticscholar.org/paper/374031be7086da4b102ece4d2be5a828790059a6}}</ref><ref name="Rosenberg 58–62"/><ref>{{Cite book|last=Rosenberg|first=L.|last2=Willcox|first2=G.|date=June 2018|title=Artificial Swarms find Social Optima : (Late Breaking Report)|journal=2018 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)|pages=174–178|doi=10.1109/COGSIMA.2018.8423987|isbn=978-1-5386-5288-6}}</ref><ref>{{Cite book|last=Rosenberg|first=L.|last2=Pescetelli|first2=N.|date=September 2017|title=Amplifying prediction accuracy using Swarm A.I.|journal=2017 Intelligent Systems Conference (IntelliSys)|pages=61–65|doi=10.1109/IntelliSys.2017.8324329|isbn=978-1-5090-6435-9}}</ref> Famously, human swarming was used to correctly predict the Kentucky Derby Superfecta, against 541 to 1 odds, in response to a challenge from reporters.<ref>{{Cite news|url=https://www.newsweek.com/artificial-intelligence-turns-20-11000-kentucky-derby-bet-457783|title=Artificial intelligence turns $20 into $11,000 in Kentucky Derby bet|date=2016-05-10|work=Newsweek|access-date=2018-09-10}}</ref> − − Enabled by mediating software such as the SWARM platform (formally unu) from Unanimous A.I., networks of distributed users can be organized into "human swarms" through the implementation of real-time closed-loop control systems. Such systems, also referred to as "Artificial Swarm Intelligence" (or the brand name Swarm AI) have been shown to significantly amplify human intelligence, resulting in a string of high-profile predictions of extreme accuracy. Academic testing shows that human swarms can out-predict individuals across a variety of real-world projections. Famously, human swarming was used to correctly predict the Kentucky Derby Superfecta, against 541 to 1 odds, in response to a challenge from reporters. − − 通过实施实时闭环控制系统，可以将分布式用户网络组织成”人群” ，从而使来自一致人工智能公司的 SWARM 平台(形式上为 unu)等中介软件成为可能。这样的系统，也被称为“人工群体智能”(或者叫做 Swarm AI) ，已经被证明可以显著地增强人类的智力，导致一系列高调的极端准确的预测。学术测试表明，通过各种现实世界的预测，人类群体可以超越个体。众所周知，人类蜂群被用来正确预测肯塔基赛马大赛，以541比1的赔率应对记者的挑战。 − − − − Medical Use of Human Swarming—in 2018, [[Stanford University School of Medicine]] and [[Unanimous A.I.|Unanimous AI]] published studies showing that groups of human doctors, when connected together by real-time swarming algorithms, could diagnose medical conditions with substantially higher accuracy than individual doctors or groups of doctors working together using traditional crowd-sourcing methods. In one such study, swarms of human radiologists connected together using the SWARM platform were tasked with diagnosing chest x-rays and demonstrated a 33% reduction in diagnostic errors as compared to the traditional human methods, and a 22% improvement over traditional machine-learning.<ref name=":4">{{Cite web|url=https://spectrum.ieee.org/the-human-os/biomedical/diagnostics/ai-human-hive-mind-diagnoses-pneumonia|title=AI-Human "Hive Mind" Diagnoses Pneumonia|last=Scudellari|first=Megan|date=2018-09-13|website=IEEE Spectrum: Technology, Engineering, and Science News|access-date=2019-07-20}}</ref><ref>{{Cite web|url=https://venturebeat.com/2018/09/10/unanimous-ai-achieves-22-more-accurate-pneumonia-diagnoses/|title=Unanimous AI achieves 22% more accurate pneumonia diagnoses|date=2018-09-10|website=VentureBeat|access-date=2019-07-20}}</ref><ref>{{Cite web|url=https://www.stanforddaily.com/2018/09/27/artificial-swarm-intelligence-diagnoses-pneumonia-better-than-individual-computer-or-doctor/|title=Artificial swarm intelligence diagnoses pneumonia better than individual computer or doctor|last=Liu|first=Fan|date=2018-09-27|website=The Stanford Daily|access-date=2019-07-20}}</ref><ref>{{Cite web|url=https://www.radiologytoday.net/archive/rt0119p12.shtml|title=A Swarm of Insight - Radiology Today Magazine|website=www.radiologytoday.net|access-date=2019-07-20}}</ref><ref name=":3">{{Cite journal|last=Rosenberg|first=Louis|last2=Lungren|first2=Matthew|last3=Halabi|first3=Safwan|last4=Willcox|first4=Gregg|last5=Baltaxe|first5=David|last6=Lyons|first6=Mimi|date=November 2018|title=Artificial Swarm Intelligence employed to Amplify Diagnostic Accuracy in Radiology|journal=2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)|location=Vancouver, BC|publisher=IEEE|pages=1186–1191|doi=10.1109/IEMCON.2018.8614883|isbn=9781538672662}}</ref> − − Medical Use of Human Swarming—in 2018, Stanford University School of Medicine and Unanimous AI published studies showing that groups of human doctors, when connected together by real-time swarming algorithms, could diagnose medical conditions with substantially higher accuracy than individual doctors or groups of doctors working together using traditional crowd-sourcing methods. In one such study, swarms of human radiologists connected together using the SWARM platform were tasked with diagnosing chest x-rays and demonstrated a 33% reduction in diagnostic errors as compared to the traditional human methods, and a 22% improvement over traditional machine-learning. − − 人类群集的医学应用ーー2018年，斯坦福大学医学院和人工智能协会共同发表了一项研究，研究表明，通过实时群集算法连接起来的人类医生群体，可以比单个医生或群体医生群体使用传统的群集外包方法诊断出更高的准确率。在其中一项研究中，一群使用 SWARM 平台联系在一起的人类放射科医生负责诊断胸部 x 光，与传统的人类方法相比，诊断错误减少了33% ，与传统的机器学习相比，改进了22% 。 − − − − ===Swarm grammars=== − − Swarm grammars are swarms of [[stochastic grammar]]s that can be evolved to describe complex properties such as found in art and architecture.<ref>{{cite journal|last1=vonMammen|first1=Sebastian|last2=Jacob|first2=Christian|title=The evolution of swarm grammars -- growing trees, crafting art and bottom-up design|journal=Computational Intelligence|volume=4|issue=3|pages=10–19|date=2009|url=http://journal.frontiersin.org/article/10.3389/fncom.2015.00090/full|doi=10.1109/MCI.2009.933096|citeseerx=10.1.1.384.9486}}</ref> These grammars interact as agents behaving according to rules of swarm intelligence. Such behavior can also suggest [[deep learning]] algorithms, in particular when mapping of such swarms to neural circuits is considered.<ref>{{cite journal|last1=du Castel|first1=Bertrand|title=Pattern Activation/Recognition Theory of Mind|journal=Frontiers in Computational Neuroscience|volume=9|issue=90|pages=90|date = 15 July 2015|doi=10.3389/fncom.2015.00090|pmid=26236228|pmc=4502584|ref=neuroscience}}</ref> − − Swarm grammars are swarms of stochastic grammars that can be evolved to describe complex properties such as found in art and architecture. These grammars interact as agents behaving according to rules of swarm intelligence. Such behavior can also suggest deep learning algorithms, in particular when mapping of such swarms to neural circuits is considered. − − 群语法是一群随机语法，可以用来描述复杂的特性，比如在艺术和建筑中发现的。这些语法相互作用，就像代理人按照群体智能规则行事一样。这种行为也可能是深度学习算法，特别是当考虑到这种群到神经回路的映射时。 − − − − ===Swarmic art=== − − In a series of works, al-Rifaie et al.<ref name=":1">{{cite journal | last1 = al-Rifaie | first1 = MM | last2 = Bishop | first2 = J.M. | last3 = Caines | first3 = S. | year = 2012 | title = Creativity and Autonomy in Swarm Intelligence Systems | url = http://research.gold.ac.uk/17273/1/2012_CC_updated.pdf| journal = Cognitive Computation | volume = 4 | issue = 3| pages = 320–331 | doi=10.1007/s12559-012-9130-y}}</ref> have successfully used two swarm intelligence algorithms—one mimicking the behaviour of one species of ants (''Leptothorax acervorum'') foraging ([[stochastic diffusion search]], SDS) and the other algorithm mimicking the behaviour of birds flocking ([[particle swarm optimization]], PSO)—to describe a novel integration strategy exploiting the local search properties of the PSO with global SDS behaviour. The resulting [[hybrid algorithm]] is used to sketch novel drawings of an input image, exploiting an artistic tension between the local behaviour of the 'birds flocking'—as they seek to follow the input sketch—and the global behaviour of the "ants foraging"—as they seek to encourage the flock to explore novel regions of the canvas. The "creativity" of this hybrid swarm system has been analysed under the philosophical light of the "rhizome" in the context of [[Deleuze]]'s "Orchid and Wasp" metaphor.<ref>Deleuze G, Guattari F, Massumi B. A thousand plateaus. Minneapolis: University of Minnesota Press; 2004.</ref> − − In a series of works, al-Rifaie et al. have successfully used two swarm intelligence algorithms—one mimicking the behaviour of one species of ants (Leptothorax acervorum) foraging (stochastic diffusion search, SDS) and the other algorithm mimicking the behaviour of birds flocking (particle swarm optimization, PSO)—to describe a novel integration strategy exploiting the local search properties of the PSO with global SDS behaviour. The resulting hybrid algorithm is used to sketch novel drawings of an input image, exploiting an artistic tension between the local behaviour of the 'birds flocking'—as they seek to follow the input sketch—and the global behaviour of the "ants foraging"—as they seek to encourage the flock to explore novel regions of the canvas. The "creativity" of this hybrid swarm system has been analysed under the philosophical light of the "rhizome" in the context of Deleuze's "Orchid and Wasp" metaphor. − − 在一系列的工作中，al-Rifaie 等人。本文介绍了一种新的集成策略，即利用粒子群优化算法的局部搜索特性和全局搜索特性，采用两种群体智能算法，一种是模仿一种蚂蚁(Leptothorax acervorum)觅食行为的算法(随机扩散搜索，SDS) ，另一种是模仿鸟类聚集行为的算法(粒子群优化粒子群优化算法，PSO)。由此产生的混合算法被用于绘制输入图像的新奇图形，利用“鸟群”的局部行为(当它们寻求跟随输入图形时)和“蚂蚁觅食”的全局行为(当它们寻求鼓励群体探索画布的新奇区域时)之间的艺术张力。本文以德勒兹的“兰花与黄蜂”隐喻为语境，以“根茎”为哲学视角，分析了这一混合群体系统的“创造性”。 − − − − A more recent work of al-Rifaie et al., "Swarmic Sketches and Attention Mechanism",<ref>{{Cite book | doi=10.1007/978-3-642-36955-1_8|chapter = Swarmic Sketches and Attention Mechanism|title = Evolutionary and Biologically Inspired Music, Sound, Art and Design| volume=7834| pages=85–96|series = Lecture Notes in Computer Science|year = 2013|last1 = Al-Rifaie|first1 = Mohammad Majid| last2=Bishop| first2=John Mark| isbn=978-3-642-36954-4| chapter-url=http://research.gold.ac.uk/17268/1/2013_EvoMUSART_sketches_April%283-5%29.pdf}}</ref> introduces a novel approach deploying the mechanism of 'attention' by adapting SDS to selectively attend to detailed areas of a digital canvas. Once the attention of the swarm is drawn to a certain line within the canvas, the capability of PSO is used to produce a 'swarmic sketch' of the attended line. The swarms move throughout the digital canvas in an attempt to satisfy their dynamic roles—attention to areas with more details—associated to them via their fitness function. Having associated the rendering process with the concepts of attention, the performance of the participating swarms creates a unique, non-identical sketch each time the 'artist' swarms embark on interpreting the input line drawings. In other works while PSO is responsible for the sketching process, SDS controls the attention of the swarm. − − A more recent work of al-Rifaie et al., "Swarmic Sketches and Attention Mechanism", introduces a novel approach deploying the mechanism of 'attention' by adapting SDS to selectively attend to detailed areas of a digital canvas. Once the attention of the swarm is drawn to a certain line within the canvas, the capability of PSO is used to produce a 'swarmic sketch' of the attended line. The swarms move throughout the digital canvas in an attempt to satisfy their dynamic roles—attention to areas with more details—associated to them via their fitness function. Having associated the rendering process with the concepts of attention, the performance of the participating swarms creates a unique, non-identical sketch each time the 'artist' swarms embark on interpreting the input line drawings. In other works while PSO is responsible for the sketching process, SDS controls the attention of the swarm. − − Al-rifaie 等人最近的工作“ Swarmic Sketches and Attention Mechanism”介绍了一种新的方法，通过调整 SDS 来选择性地注意数字画布的细节区域，从而部署“注意力”机制。一旦群体的注意力被吸引到画布上的某条线上，粒子群算法的能力就被用来产生一个被注意线的“黑色素描”。蜂群在数字画布上移动，试图满足它们的动态角色---- 注意那些有更多细节的区域---- 通过它们的适应功能与它们相关。在将绘制过程与注意力的概念联系起来之后，每当“艺术家”蜂群开始解释输入线条画时，参与蜂群的表现都会创造出一个独特的、不同的素描。在其他工作中，PSO 负责草图的绘制，SDS 控制群体的注意力。 − − − − In a similar work, "Swarmic Paintings and Colour Attention",<ref>{{Cite book | doi=10.1007/978-3-642-36955-1_9| chapter=Swarmic Paintings and Colour Attention| title=Evolutionary and Biologically Inspired Music, Sound, Art and Design| volume=7834| pages=97–108| series=Lecture Notes in Computer Science| year=2013| last1=Al-Rifaie| first1=Mohammad Majid| last2=Bishop| first2=John Mark| isbn=978-3-642-36954-4| chapter-url=http://research.gold.ac.uk/17267/1/2013_EvoMUSART_paintings_April%283-5%29.pdf}}</ref> non-photorealistic images are produced using SDS algorithm which, in the context of this work, is responsible for colour attention. − − In a similar work, "Swarmic Paintings and Colour Attention", non-photorealistic images are produced using SDS algorithm which, in the context of this work, is responsible for colour attention. − − 在一个类似的作品“ Swarmic Paintings and Colour Attention”中，使用 SDS 算法生成非真实感的图像，在这个作品中，SDS 算法负责色彩注意力。 − − − − The "computational creativity" of the above-mentioned systems are discussed in<ref name=":1" /><ref>al-Rifaie, Mohammad Majid, Mark JM Bishop, and Ahmed Aber. "[http://eprints.gold.ac.uk/6939/1/AISB_On_Creativity_of_the_swarms_ISBN%3A_978-1-908187-03-1.pdf Creative or Not? Birds and Ants Draw with Muscle]." Proceedings of AISB'11 Computing and Philosophy (2011): 23-30.</ref><ref>al-Rifaie MM, Bishop M (2013) [https://www.aaai.org/ocs/index.php/SSS/SSS13/paper/viewFile/5728/5925 Swarm intelligence and weak artificial creativity]. In: The Association for the Advancement of Artificial Intelligence (AAAI) 2013: Spring Symposium, Stanford University, Palo Alto, California, U.S.A., pp 14–19</ref> through the two prerequisites of creativity (i.e. freedom and constraints) within the swarm intelligence's two infamous phases of exploration and exploitation. − − The "computational creativity" of the above-mentioned systems are discussed in through the two prerequisites of creativity (i.e. freedom and constraints) within the swarm intelligence's two infamous phases of exploration and exploitation. − − 上述制度的「计算创造性」是透过创意的两个先决条件(即。自由和约束)在群体智能两个臭名昭著的勘探和开发阶段。 − − − − Michael Theodore and [[Nikolaus Correll]] use swarm intelligent art installation to explore what it takes to have engineered systems to appear lifelike.<ref>[http://correll.cs.colorado.edu/wp-content/uploads/correll.pdf N. Correll, N. Farrow, K. Sugawara, M. Theodore (2013): The Swarm Wall: Toward Life’s Uncanny Valley. In: K. Goldberg, H. Knight, P. Salvini (Ed.): IEEE International Conference on Robotics and Automation, Workshop on Art and Robotics: Freud's Unheimlich and the Uncanny Valley.]</ref> − − Michael Theodore and Nikolaus Correll use swarm intelligent art installation to explore what it takes to have engineered systems to appear lifelike. − − 迈克尔 · 西奥多和尼古拉斯 · 科雷尔利用群体智能艺术装置来探索如何使工程系统看起来栩栩如生。 − − − − ==Notable researchers== − − {{div col}} − − * [[Nikolaus Correll]] − − * [[Marco Dorigo]] − − * [[Russell C. Eberhart]] − − * [[Luca Maria Gambardella]] − − * [[James Kennedy (social psychologist)|James Kennedy]] − − * [[Alcherio Martinoli]] − − * [[Craig Reynolds (computer graphics)|Craig Reynolds]] − − * [[Louis B. Rosenberg|Louis Rosenberg]] − − * [[Seyedali Mirjalili]] − − * [[Magnus Egerstedt]] − − * [[Hossam Faris]] − − * [[Ibrahim Aljarah]] − − {{div col end}} − − − − ==See also== − − {{External links|date=June 2019}} − − {{Sisterlinks|Swarm Intelligence}} − − {{div col}} − − * [[Artificial immune systems]] − − * [[Collaborative intelligence]] − − * [[Collective effervescence]] − − * [[Group mind (science fiction)]] − − * [[Cellular automaton]] − − * [[Complex systems]] − − * [[Differential evolution]] − − * [[Dispersive Flies Optimisation|Dispersive flies optimisation]] − − * [[Distributed artificial intelligence]] − − * [[Evolutionary computation]] − − * [[Global brain]] − − * [[Harmony search]] − − * [[Harris hawks optimization]] − − * [[Multi-agent system]] − − * [[Myrmecology]] − − * [[Promise theory]] − − * [[Quorum sensing]] − − * [[Population protocol]] − − * [[Reinforcement learning]] − − * [[Rule 110]] − − * [[Self-organized criticality]] − − * [[Spiral optimization algorithm]] − − * [[Stochastic optimization]] − − * [[Swarm Development Group]] − − * [[Swarm robotic platforms]] − − * [[Swarming (military)|Swarming]] − − * [[SwisTrack]] − − * [[Symmetry breaking of escaping ants]] − − * ''[[The Wisdom of Crowds]]'' − − * [[Wisdom of the crowd]] − − {{div col end}} − − − − ==References== − − {{Reflist|30em}} − − − − ==Further reading== − − * {{cite book |title=Swarm Intelligence: From Natural to Artificial Systems |first1=Eric |last1=Bonabeau |first2=Marco |last2=Dorigo |first3=Guy |last3=Theraulaz |year=1999 |isbn=978-0-19-513159-8}} − − * {{cite book |title=Swarm Intelligence |first1=James |last1=Kennedy |first2=Russell C. |last2=Eberhart |isbn=978-1-55860-595-4|date=2001-04-09 }} − − * {{cite book |title=Fundamentals of Computational Swarm Intelligence |first=Andries |last=Engelbrecht |publisher=Wiley & Sons |isbn=978-0-470-09191-3|date=2005-12-16 }} − − − − == External links == − − * Marco Dorigo and Mauro Birattari (2007). [http://www.scholarpedia.org/article/Swarm_intelligence "Swarm intelligence"] in ''[[Scholarpedia]]'' − − * Antoinette Brown. [https://web.archive.org/web/20161130043122/https://medium.com/@antoinettebromwn/swarm-intelligence-review-eeb74beddbad#.xr4gpi4c6 Swarm Intelligence] − − {{animal cognition}} − − {{collective animal behaviour}} − − {{optimization algorithms|state=collapsed}} − − − − {{DEFAULTSORT:Swarm Intelligence}} − − [[Category:Nature-inspired metaheuristics| ]] − − [[Category:Collective intelligence]] 第601行：
第183行： − [[Category:Intelligence by type]]+ 第607行：
第189行： − +
Moved page from wikipedia:en:Swarm intelligence (history)
此词条暂由彩云小译翻译，翻译字数共292，未经人工整理和审校，带来阅读不便，请见谅。
{{short description|Collective behavior of decentralized, self-organized systems}}
Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence. The expression was introduced by Gerardo Beni and Jing Wang in 1989, in the context of cellular robotic systems.
'''Swarm intelligence''' ('''SI''') is the [[collective behavior]] of [[decentralization|decentralized]], [[Self-organization|self-organized]] systems, natural or artificial. The concept is employed in work on [[artificial intelligence]]. The expression was introduced by [[Gerardo Beni]] and Jing Wang in 1989, in the context of cellular robotic systems.<ref>{{cite book|author=Beni, G., Wang, J.|chapter=Swarm Intelligence in Cellular Robotic Systems|title=Proceed. NATO Advanced Workshop on Robots and Biological Systems, Tuscany, Italy, June 26–30 (1989)|pages=703–712|doi=10.1007/978-3-642-58069-7_38|year=1993|publisher=Springer|location=Berlin, Heidelberg|isbn=978-3-642-63461-1}}</ref>
Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence. The expression was introduced by Gerardo Beni and Jing Wang in 1989, in the context of cellular robotic systems. A swarm is modelled in SPP by a collection of particles that move with a constant speed but respond to a random perturbation by adopting at each time increment the average direction of motion of the other particles in their local neighbourhood. In spite of this obvious drawback it has been shown that these types of algorithms work well in practice, and have been extensively researched, and developed. ASI has also been used to enable groups of doctors to generate diagnoses with significantly higher accuracy than traditional methods.
群体智能是分散的、自组织的系统的集体行为，无论是自然的还是人为的。这个概念在人工智能工作中得到了应用。这个表达是由 Gerardo Beni 和 Jing Wang 于1989年在蜂窝机器人系统中引入的。在 SPP 模型中，群是由一组以恒定速度运动但对随机扰动作出反应的粒子组成，每次增量时采用邻域内其他粒子的平均运动方向。尽管有这个明显的缺点，但是已经证明这些类型的算法在实践中运行良好，并且已经得到了广泛的研究和开发。意大利空间局还被用于使医生群体能够以比传统方法高得多的准确度进行诊断。
SI systems consist typically of a population of simple [[Intelligent agent|agents]] or [[boids]] interacting locally with one another and with their environment. The inspiration often comes from nature, especially biological systems. The agents follow very simple rules, and although there is no centralized control structure dictating how individual agents should behave, local, and to a certain degree random, interactions between such agents lead to the [[emergence]] of "intelligent" global behavior, unknown to the individual agents. Examples of swarm intelligence in natural systems include [[ant colony|ant colonies]], bird [[flocking (behavior)|flocking]], hawks [[hunting]], animal [[herding]], [[bacteria#Growth and reproduction|bacterial growth]], fish [[shoaling and schooling|schooling]] and [[microbial intelligence]].
SI systems consist typically of a population of simple [[Intelligent agent|agents]] or [[boids]] interacting locally with one another and with their environment. The inspiration often comes from nature, especially biological systems. The agents follow very simple rules, and although there is no centralized control structure dictating how individual agents should behave, local, and to a certain degree random, interactions between such agents lead to the [[emergence]] of "intelligent" global behavior, unknown to the individual agents. Examples of swarm intelligence in natural systems include [[ant colony|ant colonies]], bird [[flocking (behavior)|flocking]], hawks [[hunting]], animal [[herding]], [[bacteria#Growth and reproduction|bacterial growth]], fish [[shoaling and schooling|schooling]] and [[microbial intelligence]].
Swarm Intelligence-based techniques can be used in a number of applications. The U.S. military is investigating swarm techniques for controlling unmanned vehicles. The European Space Agency is thinking about an orbital swarm for self-assembly and interferometry. NASA is investigating the use of swarm technology for planetary mapping. A 1992 paper by M. Anthony Lewis and George A. Bekey discusses the possibility of using swarm intelligence to control nanobots within the body for the purpose of killing cancer tumors. As published by Rosenberg (2015), such real-time systems enable groups of human participants to behave as a unified collective intelligence that works as a single entity to make predictions, answer questions, and evoke opinions. through the two prerequisites of creativity (i.e. freedom and constraints) within the swarm intelligence's two infamous phases of exploration and exploitation.
基于群体智能的技术可以应用于许多领域。美国军方正在研究用于控制无人驾驶飞行器的群技术。欧洲航天局正在考虑一个用于自组装和干涉测量的轨道群。美国宇航局正在研究群体技术在行星测绘中的应用。和 George a. Bekey 在1992年的一篇论文中讨论了使用群体智能控制人体内的纳米机器人以杀死癌症肿瘤的可能性。罗森博格(Rosenberg，2015年)发表的文章指出，这种实时系统使人类参与者的团队能够作为一个统一的集体智慧，作为一个单一的实体进行预测、回答问题和引发意见。透过创意的两个先决条件(即。自由和约束)在群体智能两个臭名昭著的勘探和开发阶段。
The application of swarm principles to [[robot]]s is called [[swarm robotics]], while 'swarm intelligence' refers to the more general set of algorithms. 'Swarm prediction' has been used in the context of forecasting problems. Similar approaches to those proposed for [[swarm robotics]] are considered for [[genetically modified organisms]] in synthetic collective intelligence. <ref>{{cite journal | vauthors = Solé R, Rodriguez-Amor D, Duran-Nebreda S, Conde-Pueyo N, Carbonell-Ballestero M, Montañez R | title = Synthetic Collective Intelligence | journal = BioSystems | volume = 148 | pages = 47–61 | date = October 2016 | doi = 10.1016/j.biosystems.2016.01.002 | pmid = 26868302 }}</ref>
The application of swarm principles to [[robot]]s is called ''[[swarm robotics]]'' while ''swarm intelligence'' refers to the more general set of algorithms. ''Swarm prediction'' has been used in the context of forecasting problems. Similar approaches to those proposed for swarm robotics are considered for [[genetically modified organisms]] in synthetic collective intelligence.<ref>{{cite journal | vauthors = Solé R, Rodriguez-Amor D, Duran-Nebreda S, Conde-Pueyo N, Carbonell-Ballestero M, Montañez R | title = Synthetic Collective Intelligence | journal = BioSystems | volume = 148 | pages = 47–61 | date = October 2016 | doi = 10.1016/j.biosystems.2016.01.002 | pmid = 26868302 }}</ref>
Michael Theodore and Nikolaus Correll use swarm intelligent art installation to explore what it takes to have engineered systems to appear lifelike.
迈克尔 · 西奥多和尼古拉斯 · 科雷尔利用群体智能艺术装置来探索如何使工程系统看起来栩栩如生。
== Models of swarm behavior ==
== Models of swarm behavior ==
Boids is an [[artificial life]] program, developed by [[Craig Reynolds (computer graphics)|Craig Reynolds]] in 1986, which simulates the [[Flocking (behavior)|flocking]] behaviour of birds. His paper on this topic was published in 1987 in the proceedings of the [[Association for Computing Machinery|ACM]] [[SIGGRAPH]] conference.<ref name = reynolds>{{Cite book
Boids is an [[artificial life]] program, developed by [[Craig Reynolds (computer graphics)|Craig Reynolds]] in 1986, which simulates the [[Flocking (behavior)|flocking]] behaviour of birds. His paper on this topic was published in 1987 in the proceedings of the [[Association for Computing Machinery|ACM]] [[SIGGRAPH]] conference.<ref name = reynolds>{{Cite book
| last1=Reynolds
| last1=Reynolds
| first1=Craig
| first1=Craig
| first1=Craig
| s2cid=546350
| author1-link=Craig Reynolds (computer_graphics)
| author1-link=Craig Reynolds (computer_graphics)
| title=Flocks, herds and schools: A distributed behavioral model.
| title=Flocks, herds and schools: A distributed behavioral model.
| year=1987
| year=1987
| volume=
| volume=
| number=
| number=
| journal=SIGGRAPH '87: Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques
| journal=SIGGRAPH '87: Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques
| publisher=[[Association for Computing Machinery]]
| publisher=[[Association for Computing Machinery]]
| pages=25–34
| pages=25–34
| isbn=978-0-89791-227-3
| isbn=978-0-89791-227-3
| doi=10.1145/37401.37406
| doi=10.1145/37401.37406
| citeseerx=10.1.1.103.7187
| citeseerx=10.1.1.103.7187
}}</ref>
}}</ref>
The name "boid" corresponds to a shortened version of "bird-oid object", which refers to a bird-like object.<ref>{{Cite journal
The name "boid" corresponds to a shortened version of "bird-oid object", which refers to a bird-like object.<ref>{{Cite journal
| last1=Banks
| last1=Banks
| first1=Alec
| first1=Alec
| last2=Vincent
| last2=Vincent
| first2=Jonathan
| first2=Jonathan
| last3=Anyakoha
| last3=Anyakoha
| first3=Chukwudi
| first3=Chukwudi
| s2cid=2344624
| title=A review of particle swarm optimization. Part I: background and development
| title=A review of particle swarm optimization. Part I: background and development
| title=A review of particle swarm optimization. Part I: background and development
|date=July 2007
|date=July 2007
| volume=6
| volume=6
| issue=4
| issue=4
| pages=467–484
| pages=467–484
| journal=Natural Computing
| journal=Natural Computing
| doi=10.1007/s11047-007-9049-5
| doi=10.1007/s11047-007-9049-5
| citeseerx=10.1.1.605.5879
| citeseerx=10.1.1.605.5879
}}</ref>
}}</ref>
As with most artificial life simulations, Boids is an example of [[emergence|emergent]] behavior; that is, the complexity of Boids arises from the interaction of individual agents (the boids, in this case) adhering to a set of simple rules. The rules applied in the simplest Boids world are as follows:
As with most artificial life simulations, Boids is an example of [[emergence|emergent]] behavior; that is, the complexity of Boids arises from the interaction of individual agents (the boids, in this case) adhering to a set of simple rules. The rules applied in the simplest Boids world are as follows:
More complex rules can be added, such as obstacle avoidance and goal seeking.
More complex rules can be added, such as obstacle avoidance and goal seeking.
{{main|Self-propelled particles}}
{{main|Self-propelled particles}}
Self-propelled particles (SPP), also referred to as the ''Vicsek model'', was introduced in 1995 by [[Tamás Vicsek|Vicsek]] ''et al.''<ref name="Vicsek1995">{{cite journal | last1 = Vicsek | first1 = T. |authorlink1=Tamás Vicsek| last2 = Czirok | first2 = A. | last3 = Ben-Jacob | first3 = E. | last4 = Cohen | first4 = I. | last5 = Shochet | first5 = O. | year = 1995 | arxiv = cond-mat/0611743 | title = Novel type of phase transition in a system of self-driven particles | journal = [[Physical Review Letters]] | volume = 75 | issue = 6 | pages = 1226–1229 | doi = 10.1103/PhysRevLett.75.1226 | pmid=10060237|bibcode = 1995PhRvL..75.1226V }}</ref> as a special case of the [[boids]] model introduced in 1986 by [[Craig Reynolds (computer graphics)|Reynolds]].<ref name="reynolds" /> A swarm is modelled in SPP by a collection of particles that move with a constant speed but respond to a random perturbation by adopting at each time increment the average direction of motion of the other particles in their local neighbourhood.<ref>{{cite journal | last1 = Czirók | first1 = A. | last2 = Vicsek | first2 = T. | year = 2006 | arxiv = cond-mat/0611742 | title = Collective behavior of interacting self-propelled particles | journal = [[Physica A]] | volume = 281 | issue = 1 | pages = 17–29 | doi = 10.1016/S0378-4371(00)00013-3 | bibcode=2000PhyA..281...17C}}</ref> SPP models predict that swarming animals share certain properties at the group level, regardless of the type of animals in the swarm.<ref name="Buhl et al">{{cite journal | last1 = Buhl | first1 = J. | last2 = Sumpter | first2 = D.J.T. | last3 = Couzin | first3 = D. | last4 = Hale | first4 = J.J. | last5 = Despland | first5 = E. | last6 = Miller | first6 = E.R. | last7 = Simpson | first7 = S.J.| year = 2006 | title = From disorder to order in marching locusts | url = http://webscript.princeton.edu/~icouzin/website/wp-content/plugins/bib2html/data/papers/buhl06.pdf | journal = Science | volume = 312 | issue = 5778| pages = 1402–1406 | doi = 10.1126/science.1125142 | pmid = 16741126 |bibcode = 2006Sci...312.1402B |display-authors=etal}}</ref> Swarming systems give rise to [[emergent behaviour]]s which occur at many different scales, some of which are turning out to be both universal and robust. It has become a challenge in theoretical physics to find minimal statistical models that capture these behaviours.<ref>{{cite journal | last1 = Toner | first1 = J. | last2 = Tu | first2 = Y. | last3 = Ramaswamy | first3 = S. | year = 2005 | title = Hydrodynamics and phases of flocks | url = http://eprints.iisc.ernet.in/3397/1/A89.pdf | journal = Annals of Physics | volume = 318 | issue = 1| pages = 170–244 |bibcode = 2005AnPhy.318..170T |doi = 10.1016/j.aop.2005.04.011 }}</ref><ref name="Bertin et al">{{cite journal | last1 = Bertin | first1 = E. | last2 = Droz | first2 = M. | last3 = Grégoire | first3 = G. | year = 2009 | arxiv = 0907.4688 | title = Hydrodynamic equations for self-propelled particles: microscopic derivation and stability analysis | journal = [[J. Phys. A]] | volume = 42 | issue = 44 | page = 445001 | doi = 10.1088/1751-8113/42/44/445001 |bibcode = 2009JPhA...42R5001B }}</ref><ref name="Li et al">{{cite journal | last1 = Li | first1 = Y.X. | last2 = Lukeman | first2 = R. | last3 = Edelstein-Keshet | first3 = L. | year = 2007 | title = Minimal mechanisms for school formation in self-propelled particles | url = http://www.iam.ubc.ca/~lukeman/fish_school_f.pdf | journal = Physica D: Nonlinear Phenomena | volume = 237 | issue = 5 | pages = 699–720 | doi = 10.1016/j.physd.2007.10.009 | bibcode = 2008PhyD..237..699L | display-authors = etal }}{{dead link|date=December 2017 |bot=InternetArchiveBot |fix-attempted=yes }}</ref>
Self-propelled particles (SPP), also referred to as the ''Vicsek model'', was introduced in 1995 by [[Tamás Vicsek|Vicsek]] ''et al.''<ref name="Vicsek1995">{{cite journal | last1 = Vicsek | first1 = T. |authorlink1=Tamás Vicsek| last2 = Czirok | first2 = A. | last3 = Ben-Jacob | first3 = E. | last4 = Cohen | first4 = I. | last5 = Shochet | first5 = O. | s2cid = 15918052 | year = 1995 | arxiv = cond-mat/0611743 | title = Novel type of phase transition in a system of self-driven particles | journal = [[Physical Review Letters]] | volume = 75 | issue = 6 | pages = 1226–1229 | doi = 10.1103/PhysRevLett.75.1226 | pmid=10060237|bibcode = 1995PhRvL..75.1226V }}</ref> as a special case of the [[boids]] model introduced in 1986 by [[Craig Reynolds (computer graphics)|Reynolds]].<ref name="reynolds" /> A swarm is modelled in SPP by a collection of particles that move with a constant speed but respond to a random perturbation by adopting at each time increment the average direction of motion of the other particles in their local neighbourhood.<ref>{{cite journal | last1 = Czirók | first1 = A. | last2 = Vicsek | first2 = T. | s2cid = 14211016 | year = 2006 | arxiv = cond-mat/0611742 | title = Collective behavior of interacting self-propelled particles | journal = [[Physica A]] | volume = 281 | issue = 1 | pages = 17–29 | doi = 10.1016/S0378-4371(00)00013-3 | bibcode=2000PhyA..281...17C}}</ref> SPP models predict that swarming animals share certain properties at the group level, regardless of the type of animals in the swarm.<ref name="Buhl et al">{{cite journal | last1 = Buhl | first1 = J. | last2 = Sumpter | first2 = D.J.T. | last3 = Couzin | first3 = D. | last4 = Hale | first4 = J.J. | last5 = Despland | first5 = E. | last6 = Miller | first6 = E.R. | last7 = Simpson | first7 = S.J.| s2cid = 359329 | year = 2006 | title = From disorder to order in marching locusts | url = http://webscript.princeton.edu/~icouzin/website/wp-content/plugins/bib2html/data/papers/buhl06.pdf | journal = Science | volume = 312 | issue = 5778| pages = 1402–1406 | doi = 10.1126/science.1125142 | pmid = 16741126 |bibcode = 2006Sci...312.1402B |display-authors=etal}}</ref> Swarming systems give rise to [[emergent behaviour]]s which occur at many different scales, some of which are turning out to be both universal and robust. It has become a challenge in theoretical physics to find minimal statistical models that capture these behaviours.<ref>{{cite journal | last1 = Toner | first1 = J. | last2 = Tu | first2 = Y. | last3 = Ramaswamy | first3 = S. | year = 2005 | title = Hydrodynamics and phases of flocks | url = http://eprints.iisc.ernet.in/3397/1/A89.pdf | journal = Annals of Physics | volume = 318 | issue = 1| pages = 170–244 |bibcode = 2005AnPhy.318..170T |doi = 10.1016/j.aop.2005.04.011 }}</ref><ref name="Bertin et al">{{cite journal | last1 = Bertin | first1 = E. | last2 = Droz | first2 = M. | last3 = Grégoire | first3 = G. | s2cid = 17686543 | year = 2009 | arxiv = 0907.4688 | title = Hydrodynamic equations for self-propelled particles: microscopic derivation and stability analysis | journal = [[J. Phys. A]] | volume = 42 | issue = 44 | page = 445001 | doi = 10.1088/1751-8113/42/44/445001 |bibcode = 2009JPhA...42R5001B }}</ref><ref name="Li et al">{{cite journal | last1 = Li | first1 = Y.X. | last2 = Lukeman | first2 = R. | last3 = Edelstein-Keshet | first3 = L. | year = 2007 | title = Minimal mechanisms for school formation in self-propelled particles | url = http://www.iam.ubc.ca/~lukeman/fish_school_f.pdf | journal = Physica D: Nonlinear Phenomena | volume = 237 | issue = 5 | pages = 699–720 | doi = 10.1016/j.physd.2007.10.009 | bibcode = 2008PhyD..237..699L | display-authors = etal }}{{dead link|date=December 2017 |bot=InternetArchiveBot |fix-attempted=yes }}</ref>
{{see also|List of metaphor-based metaheuristics}}
{{see also|List of metaphor-based metaheuristics}}
[[Evolutionary algorithm]]s (EA), [[particle swarm optimization]] (PSO), [[differential evolution]] (DE), [[ant colony optimization]] (ACO) and their variants dominate the field of nature-inspired [[metaheuristic]]s.<ref>{{cite book|first=Michael A.|last=Lones|year=2014|title=Metaheuristics in Nature-Inspired Algorithms|journal=[[Genetic and Evolutionary Computation Conference|GECCO '14]]|pages=1419–1422|url=http://www.macs.hw.ac.uk/~ml355/common/papers/lones-gecco2014-metaheuristics.pdf|doi=10.1145/2598394.2609841|isbn=9781450328814|citeseerx=10.1.1.699.1825}}</ref> This list includes algorithms published up to circa the year 2000. A large number of more recent metaphor-inspired metaheuristics have started to [[List of metaphor-inspired metaheuristics#Criticism|attract criticism in the research community]] for hiding their lack of novelty behind an elaborate metaphor. For algorithms published since that time, see [[List of metaphor-based metaheuristics]].
[[Evolutionary algorithm]]s (EA), [[particle swarm optimization]] (PSO), [[differential evolution]] (DE), [[ant colony optimization]] (ACO) and their variants dominate the field of nature-inspired [[metaheuristic]]s.<ref>{{cite book|first=Michael A.|last=Lones|title=Proceedings of the 2014 conference companion on Genetic and evolutionary computation companion - GECCO Comp '14|s2cid=14997975|year=2014|chapter=Metaheuristics in Nature-Inspired Algorithms|journal=[[Genetic and Evolutionary Computation Conference|GECCO '14]]|pages=1419–1422|url=http://www.macs.hw.ac.uk/~ml355/common/papers/lones-gecco2014-metaheuristics.pdf|doi=10.1145/2598394.2609841|isbn=9781450328814|citeseerx=10.1.1.699.1825}}</ref> This list includes algorithms published up to circa the year 2000. A large number of more recent metaphor-inspired metaheuristics have started to [[List of metaphor-inspired metaheuristics#Criticism|attract criticism in the research community]] for hiding their lack of novelty behind an elaborate metaphor. For algorithms published since that time, see [[List of metaphor-based metaheuristics]].
It should also be noted that [[metaheuristic]]s, as good as they are, lack a confidence in a solution.<ref name="Silberholz 2019 581–604">{{Citation|last1=Silberholz|first1=John|title=Computational Comparison of Metaheuristics|date=2019|work=Handbook of Metaheuristics|pages=581–604|editor-last=Gendreau|editor-first=Michel|series=International Series in Operations Research & Management Science|place=Cham|publisher=Springer International Publishing|language=en|doi=10.1007/978-3-319-91086-4_18|isbn=978-3-319-91086-4|last2=Golden|first2=Bruce|last3=Gupta|first3=Swati|last4=Wang|first4=Xingyin|editor2-last=Potvin|editor2-first=Jean-Yves}}</ref> When appropriate parameters are determined, and when sufficient convergence stage is achieved, they often find a solution that is optimal, or near close to optimum – nevertheless, if one does not know optimal solution in advance, a quality of a solution is not known.<ref name="Silberholz 2019 581–604"/> In spite of this obvious drawback it has been shown that these types of [[algorithm]]s work well in practice, and have been extensively researched, and developed.<ref>{{Citation|last1=Burke|first1=Edmund|title=Variable Neighborhood Search for Nurse Rostering Problems|date=2004|work=Metaheuristics: Computer Decision-Making|pages=153–172|editor-last=Resende|editor-first=Mauricio G. C.|series=Applied Optimization|place=Boston, MA|publisher=Springer US|language=en|doi=10.1007/978-1-4757-4137-7_7|isbn=978-1-4757-4137-7|last2=De Causmaecker|first2=Patrick|last3=Petrovic|first3=Sanja|last4=Berghe|first4=Greet Vanden|editor2-last=de Sousa|editor2-first=Jorge Pinho}}</ref><ref>{{Cite journal|last=Fu|first=Michael C.|date=2002-08-01|title=Feature Article: Optimization for simulation: Theory vs. Practice|journal=INFORMS Journal on Computing|volume=14|issue=3|pages=192–215|doi=10.1287/ijoc.14.3.192.113|issn=1091-9856}}</ref><ref>{{Cite journal|last1=Dorigo|first1=Marco|last2=Birattari|first2=Mauro|last3=Stutzle|first3=Thomas|date=November 2006|title=Ant colony optimization|journal=IEEE Computational Intelligence Magazine|volume=1|issue=4|pages=28–39|doi=10.1109/MCI.2006.329691|issn=1556-603X}}</ref><ref>{{Cite journal|last=Hayes-RothFrederick|date=1975-08-01|title=Review of "Adaptation in Natural and Artificial Systems by John H. Holland", The U. of Michigan Press, 1975|journal=ACM SIGART Bulletin|issue=53|page=15|language=EN|doi=10.1145/1216504.1216510|s2cid=14985677}}</ref><ref>{{Citation|last1=Resende|first1=Mauricio G.C.|title=Greedy Randomized Adaptive Search Procedures: Advances, Hybridizations, and Applications|date=2010|work=Handbook of Metaheuristics|pages=283–319|editor-last=Gendreau|editor-first=Michel|series=International Series in Operations Research & Management Science|place=Boston, MA|publisher=Springer US|language=en|doi=10.1007/978-1-4419-1665-5_10|isbn=978-1-4419-1665-5|last2=Ribeiro|first2=Celso C.|editor2-last=Potvin|editor2-first=Jean-Yves}}</ref> On the other hand, it is possible to avoid this drawback by calculating solution quality for a special case where such calculation is possible, and after such run it is known that every solution that is at least as good as the solution a special case had, has at least a solution confidence a special case had. One such instance is [[Ant colony optimization algorithms|Ant]] inspired [[Monte Carlo algorithm]] for [[Minimum feedback arc set|Minimum Feedback Arc Set]] where this has been achieved probabilistically via hybridization of [[Monte Carlo algorithm]] with [[Ant colony optimization algorithms|Ant Colony Optimization]] technique.<ref>{{Cite journal|last1=Kudelić|first1=Robert|last2=Ivković|first2=Nikola|date=2019-05-15|title=Ant inspired Monte Carlo algorithm for minimum feedback arc set|url=http://www.sciencedirect.com/science/article/pii/S0957417418307899|journal=Expert Systems with Applications|language=en|volume=122|pages=108–117|doi=10.1016/j.eswa.2018.12.021|issn=0957-4174}}</ref>
{{main|Stochastic diffusion search}}
{{main|Stochastic diffusion search}}
First published in 1989 Stochastic diffusion search (SDS)<ref>Bishop, J.M., [http://www.reading.ac.uk/web/files/sse/sds-ssn.pdf Stochastic Searching Networks], Proc. 1st IEE Int. Conf. on Artificial Neural Networks, pp. 329-331, London, UK, (1989).</ref><ref>Nasuto, S.J. & Bishop, J.M., (2008), [https://www.researchgate.net/profile/Slawomir_Nasuto/publication/225352594_Stabilizing_Swarm_Intelligence_Search_via_Positive_Feedback_Resource_Allocation/links/02e7e51d316b96f609000000.pdf Stabilizing swarm intelligence search via positive feedback resource allocation], In: Krasnogor, N., Nicosia, G, Pavone, M., & Pelta, D. (eds), Nature Inspired Cooperative Strategies for Optimization, Studies in Computational Intelligence, vol 129, Springer, Berlin, Heidelberg, New York, pp. 115-123.</ref> was the first Swarm Intelligence metaheuristic. SDS is an agent-based [[Probabilistic algorithm|probabilistic]] global search and optimization technique best suited to problems where the objective function can be decomposed into multiple independent partial-functions. Each agent maintains a hypothesis which is iteratively tested by evaluating a randomly selected partial objective function parameterised by the agent's current hypothesis. In the standard version of SDS such partial function evaluations are binary, resulting in each agent becoming active or inactive. Information on hypotheses is diffused across the population via inter-agent communication. Unlike the [[Stigmergy|stigmergic]] communication used in ACO, in SDS agents communicate [[hypothesis|hypotheses]] via a one-to-one communication strategy analogous to the [[tandem running]] procedure observed in [[Leptothorax acervorum]].<ref>Moglich, M.; Maschwitz, U.; Holldobler, B., [https://science.sciencemag.org/content/186/4168/1046.short Tandem Calling: A New Kind of Signal in Ant Communication], Science, Volume 186, Issue 4168, pp. 1046-1047</ref> A positive feedback mechanism ensures that, over time, a population of agents stabilise around the global-best solution. SDS is both an efficient and robust global search and optimisation algorithm, which has been extensively mathematically described.<ref>Nasuto, S.J., Bishop, J.M. & Lauria, S., [http://www.reading.ac.uk/web/files/sse/sds-time.pdf Time complexity analysis of the Stochastic Diffusion Search], Proc. Neural Computation '98, pp. 260-266, Vienna, Austria, (1998).</ref><ref>Nasuto, S.J., & Bishop, J.M., (1999), Convergence of the Stochastic Diffusion Search, Parallel Algorithms, 14:2, pp: 89-107.</ref><ref>Myatt, D.M., Bishop, J.M., Nasuto, S.J., (2004), [https://pdfs.semanticscholar.org/be33/46c0e081b0d17ec8763c95d00401b7ee29e9.pdf Minimum stable convergence criteria for Stochastic Diffusion Search], Electronics Letters, 22:40, pp. 112-113.</ref> Recent work has involved merging the global search properties of SDS with other swarm intelligence algorithms.<ref>al-Rifaie, M.M., Bishop, J.M. & Blackwell, T., [http://gala.gre.ac.uk/21044/13/21044%20AL-RIFAIE_Stochastic_Diffusion_Search_and%20Particle_Swarm_Optimisation_2011.pdf An investigation into the merger of stochastic diffusion search and particle swarm optimisation], Proc. 13th Conf. Genetic and Evolutionary Computation, (GECCO), pp.37-44, (2012).</ref><ref>al-Rifaie, Mohammad Majid, John Mark Bishop, and Tim Blackwell. "[https://eprints.goldsmiths.ac.uk/17271/1/2012_MC.pdf Information sharing impact of stochastic diffusion search on differential evolution algorithm]." Memetic Computing 4.4 (2012): 327-338.</ref>
First published in 1989 Stochastic diffusion search (SDS)<ref>Bishop, J.M., [http://www.reading.ac.uk/web/files/sse/sds-ssn.pdf Stochastic Searching Networks], Proc. 1st IEE Int. Conf. on Artificial Neural Networks, pp. 329-331, London, UK, (1989).</ref><ref>Nasuto, S.J. & Bishop, J.M., (2008), [https://www.researchgate.net/profile/Slawomir_Nasuto/publication/225352594_Stabilizing_Swarm_Intelligence_Search_via_Positive_Feedback_Resource_Allocation/links/02e7e51d316b96f609000000.pdf Stabilizing swarm intelligence search via positive feedback resource allocation], In: Krasnogor, N., Nicosia, G, Pavone, M., & Pelta, D. (eds), Nature Inspired Cooperative Strategies for Optimization, Studies in Computational Intelligence, vol 129, Springer, Berlin, Heidelberg, New York, pp. 115-123.</ref> was the first Swarm Intelligence metaheuristic. SDS is an agent-based [[Probabilistic algorithm|probabilistic]] global search and optimization technique best suited to problems where the objective function can be decomposed into multiple independent partial-functions. Each agent maintains a hypothesis that is iteratively tested by evaluating a randomly selected partial objective function parameterised by the agent's current hypothesis. In the standard version of SDS such partial function evaluations are binary, resulting in each agent becoming active or inactive. Information on hypotheses is diffused across the population via inter-agent communication. Unlike the [[Stigmergy|stigmergic]] communication used in ACO, in SDS agents communicate [[hypothesis|hypotheses]] via a one-to-one communication strategy analogous to the [[tandem running]] procedure observed in [[Leptothorax acervorum]].<ref>Moglich, M.; Maschwitz, U.; Holldobler, B., [https://science.sciencemag.org/content/186/4168/1046.short Tandem Calling: A New Kind of Signal in Ant Communication], Science, Volume 186, Issue 4168, pp. 1046-1047</ref> A positive feedback mechanism ensures that, over time, a population of agents stabilise around the global-best solution. SDS is both an efficient and robust global search and optimisation algorithm, which has been extensively mathematically described.<ref>Nasuto, S.J., Bishop, J.M. & Lauria, S., [http://www.reading.ac.uk/web/files/sse/sds-time.pdf Time complexity analysis of the Stochastic Diffusion Search], Proc. Neural Computation '98, pp. 260-266, Vienna, Austria, (1998).</ref><ref>Nasuto, S.J., & Bishop, J.M., (1999), Convergence of the Stochastic Diffusion Search, Parallel Algorithms, 14:2, pp: 89-107.</ref><ref>Myatt, D.M., Bishop, J.M., Nasuto, S.J., (2004), [https://pdfs.semanticscholar.org/be33/46c0e081b0d17ec8763c95d00401b7ee29e9.pdf Minimum stable convergence criteria for Stochastic Diffusion Search], Electronics Letters, 22:40, pp. 112-113.</ref> Recent work has involved merging the global search properties of SDS with other swarm intelligence algorithms.<ref>al-Rifaie, M.M., Bishop, J.M. & Blackwell, T., [http://gala.gre.ac.uk/21044/13/21044%20AL-RIFAIE_Stochastic_Diffusion_Search_and%20Particle_Swarm_Optimisation_2011.pdf An investigation into the merger of stochastic diffusion search and particle swarm optimisation], Proc. 13th Conf. Genetic and Evolutionary Computation, (GECCO), pp.37-44, (2012).</ref><ref>al-Rifaie, Mohammad Majid, John Mark Bishop, and Tim Blackwell. "[https://eprints.goldsmiths.ac.uk/17271/1/2012_MC.pdf Information sharing impact of stochastic diffusion search on differential evolution algorithm]." Memetic Computing 4.4 (2012): 327-338.</ref>
Ant colony optimization (ACO), introduced by Dorigo in his doctoral dissertation, is a class of [[Optimization (mathematics)|optimization]] [[algorithm]]s modeled on the actions of an [[ant colony]]. ACO is a [[Probabilistic algorithm|probabilistic technique]] useful in problems that deal with finding better paths through graphs. Artificial 'ants'—simulation agents—locate optimal solutions by moving through a [[parameter space]] representing all possible solutions. Natural ants lay down [[pheromone]]s directing each other to resources while exploring their environment. The simulated 'ants' similarly record their positions and the quality of their solutions, so that in later simulation iterations more ants locate for better solutions.<ref>Ant Colony Optimization by Marco Dorigo and Thomas Stützle, MIT Press, 2004. {{ISBN|0-262-04219-3}}</ref>
Ant colony optimization (ACO), introduced by Dorigo in his doctoral dissertation, is a class of [[Optimization (mathematics)|optimization]] [[algorithm]]s modeled on the actions of an [[ant colony]]. ACO is a [[Probabilistic algorithm|probabilistic technique]] useful in problems that deal with finding better paths through graphs. Artificial 'ants'—simulation agents—locate optimal solutions by moving through a [[parameter space]] representing all possible solutions. Natural ants lay down [[pheromone]]s directing each other to resources while exploring their environment. The simulated 'ants' similarly record their positions and the quality of their solutions, so that in later simulation iterations more ants locate for better solutions.<ref>Ant Colony Optimization by Marco Dorigo and Thomas Stützle, MIT Press, 2004. {{ISBN|0-262-04219-3}}</ref>
{{main|Particle swarm optimization}}
{{main|Particle swarm optimization}}
Particle swarm optimization (PSO) is a [[global optimization]] algorithm for dealing with problems in which a best solution can be represented as a point or surface in an n-dimensional space. Hypotheses are plotted in this space and seeded with an initial [[velocity]], as well as a communication channel between the particles.<ref>{{cite journal |doi=10.1023/A:1016568309421 |title=Recent Approaches to Global Optimization Problems Through Particle Swarm Optimization |last=Parsopoulos |first=K. E. |last2=Vrahatis |first2=M. N. |journal=Natural Computing |volume=1 |issue=2–3 |pages=235–306 |year=2002 |url=https://www.semanticscholar.org/paper/30dd2516a900a15d95c94be6064130642b3f8447 }}</ref><ref>[http://www.iste.co.uk/?searchtext=clerc&ACTION=Search&cat=&ACTION=Search Particle Swarm Optimization] by Maurice Clerc, ISTE, {{ISBN|1-905209-04-5}}, 2006.</ref> Particles then move through the solution space, and are evaluated according to some [[fitness (biology)|fitness]] criterion after each timestep. Over time, particles are accelerated towards those particles within their communication grouping which have better fitness values. The main advantage of such an approach over other global minimization strategies such as [[simulated annealing]] is that the large number of members that make up the particle swarm make the technique impressively resilient to the problem of [[local minima]].
Particle swarm optimization (PSO) is a [[global optimization]] algorithm for dealing with problems in which a best solution can be represented as a point or surface in an n-dimensional space. Hypotheses are plotted in this space and seeded with an initial [[velocity]], as well as a communication channel between the particles.<ref>{{cite journal |doi=10.1023/A:1016568309421 |title=Recent Approaches to Global Optimization Problems Through Particle Swarm Optimization |last1=Parsopoulos |first1=K. E. |last2=Vrahatis |first2=M. N. |s2cid=4021089 |journal=Natural Computing |volume=1 |issue=2–3 |pages=235–306 |year=2002 }}</ref><ref>[http://www.iste.co.uk/?searchtext=clerc&ACTION=Search&cat=&ACTION=Search Particle Swarm Optimization] by Maurice Clerc, ISTE, {{ISBN|1-905209-04-5}}, 2006.</ref> Particles then move through the solution space, and are evaluated according to some [[fitness (biology)|fitness]] criterion after each timestep. Over time, particles are accelerated towards those particles within their communication grouping which have better fitness values. The main advantage of such an approach over other global minimization strategies such as [[simulated annealing]] is that the large number of members that make up the particle swarm make the technique impressively resilient to the problem of [[local minima]].
=== Artificial Swarm Intelligence (2015) ===
=== Artificial Swarm Intelligence (2015) ===
Artificial Swarm Intelligence (ASI) is method of amplifying the collective intelligence of networked human groups using control algorithms modeled after natural swarms. Sometimes referred to as Human Swarming or Swarm AI, the technology connects groups of human participants into real-time systems that deliberate and converge on solutions as dynamic swarms when simultaneously presented with a question<ref>{{Cite book|last=Rosenberg|first=Louis|date=2015-07-20|chapter=Human Swarms, a real-time method for collective intelligence|chapter-url=https://www.mitpressjournals.org/doi/abs/10.1162/978-0-262-33027-5-ch117|volume=27|pages=658–659|doi=10.7551/978-0-262-33027-5-ch117|isbn=9780262330275|via=|title=07/20/2015-07/24/2015}}</ref><ref name=":0" /><ref>{{Cite journal|last=Metcalf|first=Lynn|last2=Askay|first2=David A.|last3=Rosenberg|first3=Louis B.|date=2019|title=Keeping Humans in the Loop: Pooling Knowledge through Artificial Swarm Intelligence to Improve Business Decision Making|journal=California Management Review|language=en|volume=61|issue=4|pages=84–109|doi=10.1177/0008125619862256|issn=0008-1256}}</ref> ASI has been used for a wide range of applications, from enabling business teams to generate highly accurate financial forecasts<ref>{{Cite book |doi = 10.1109/HCC46620.2019.00019|chapter = "Human Swarming" Amplifies Accuracy and ROI when Forecasting Financial Markets|title = 2019 IEEE International Conference on Humanized Computing and Communication (HCC)|pages = 77–82|year = 2019|last1 = Schumann|first1 = Hans|last2 = Willcox|first2 = Gregg|last3 = Rosenberg|first3 = Louis|last4 = Pescetelli|first4 = Niccolo|isbn = 978-1-7281-4125-1|chapter-url = https://www.semanticscholar.org/paper/1f64f831a9ac3f7e55fa30299099b2dbc893506e}}</ref> to enabling sports fans to outperform Vegas betting markets.<ref name=":2" /> ASI has also been used to enable groups of doctors to generate diagnoses with significantly higher accuracy than traditional methods.<ref name=":4" /><ref name=":3" />
Artificial Swarm Intelligence (ASI) is method of amplifying the collective intelligence of networked human groups using control algorithms modeled after natural swarms. Sometimes referred to as Human Swarming or Swarm AI, the technology connects groups of human participants into real-time systems that deliberate and converge on solutions as dynamic swarms when simultaneously presented with a question<ref>{{Cite book|last=Rosenberg|first=Louis|date=2015-07-20|chapter=Human Swarms, a real-time method for collective intelligence|chapter-url=https://www.mitpressjournals.org/doi/abs/10.1162/978-0-262-33027-5-ch117|volume=27|pages=658–659|doi=10.7551/978-0-262-33027-5-ch117|isbn=9780262330275|via=|title=07/20/2015-07/24/2015}}</ref><ref name=":0" /><ref>{{Cite journal|last1=Metcalf|first1=Lynn|last2=Askay|first2=David A.|last3=Rosenberg|first3=Louis B.|s2cid=202323483|date=2019|title=Keeping Humans in the Loop: Pooling Knowledge through Artificial Swarm Intelligence to Improve Business Decision Making|journal=California Management Review|language=en|volume=61|issue=4|pages=84–109|doi=10.1177/0008125619862256|issn=0008-1256}}</ref> ASI has been used for a wide range of applications, from enabling business teams to generate highly accurate financial forecasts<ref>{{Cite book |doi = 10.1109/HCC46620.2019.00019|chapter = "Human Swarming" Amplifies Accuracy and ROI when Forecasting Financial Markets|title = 2019 IEEE International Conference on Humanized Computing and Communication (HCC)|pages = 77–82|year = 2019|last1 = Schumann|first1 = Hans|last2 = Willcox|first2 = Gregg|last3 = Rosenberg|first3 = Louis|last4 = Pescetelli|first4 = Niccolo|s2cid = 209496644|isbn = 978-1-7281-4125-1}}</ref> to enabling sports fans to outperform Vegas betting markets.<ref name=":2" /> ASI has also been used to enable groups of doctors to generate diagnoses with significantly higher accuracy than traditional methods.<ref name=":4" /><ref name=":3" />
==Applications==
==Applications==
Swarm Intelligence-based techniques can be used in a number of applications. The U.S. military is investigating swarm techniques for controlling unmanned vehicles. The [[European Space Agency]] is thinking about an orbital swarm for self-assembly and interferometry. [[NASA]] is investigating the use of swarm technology for planetary mapping. A 1992 paper by [[M. Anthony Lewis (roboticist)|M. Anthony Lewis]] and [[George A. Bekey]] discusses the possibility of using swarm intelligence to control nanobots within the body for the purpose of killing cancer tumors.<ref>{{cite journal |last=Lewis |first=M. Anthony |last2=Bekey |first2=George A. |title=The Behavioral Self-Organization of Nanorobots Using Local Rules |journal=Proceedings of the 1992 IEEE/RSJ International Conference on Intelligent Robots and Systems |url=https://www.researchgate.net/publication/3690783}}</ref> Conversely al-Rifaie and Aber have used [[stochastic diffusion search]] to help locate tumours.<ref>{{cite journal | last1 = al-Rifaie | first1 = M.M. | last2 = Aber | first2 = A. | year = | title = Identifying metastasis in bone scans with Stochastic Diffusion Search | url =https://www.researchgate.net/publication/262223271 | journal = Proc. IEEE Information Technology in Medicine and Education, ITME | volume = 2012 | issue = | pages = 519–523 }}</ref><ref>al-Rifaie, Mohammad Majid, Ahmed Aber, and Ahmed Majid Oudah. "[http://www.academia.edu/download/30759619/Utilising-Stochastic-Diffusion-Search.pdf Utilising Stochastic Diffusion Search to identify metastasis in bone scans and microcalcifications on mammographs]." In Bioinformatics and Biomedicine Workshops (BIBMW), 2012 IEEE International Conference on, pp. 280-287. IEEE, 2012.</ref> Swarm intelligence has also been applied for [[data mining]].<ref>{{cite journal |first=D. |last=Martens |first2=B. |last2=Baesens |first3=T. |last3=Fawcett |title=Editorial Survey: Swarm Intelligence for Data Mining |journal=Machine Learning |volume=82 |issue=1 |pages=1–42 |year=2011 |doi=10.1007/s10994-010-5216-5 |doi-access=free }}</ref> Ant based models are further subject of modern management theory.<ref>{{cite book |last1=Fladerer |first1=Johannes-Paul |last2=Kurzmann |first2=Ernst |title=THE WISDOM OF THE MANY : how to create self -organisation and how to use collective... intelligence in companies and in society from mana. |date=November 2019 |publisher=BOOKS ON DEMAND |isbn=9783750422421}}</ref>
Swarm Intelligence-based techniques can be used in a number of applications. The U.S. military is investigating swarm techniques for controlling unmanned vehicles. The [[European Space Agency]] is thinking about an orbital swarm for self-assembly and interferometry. [[NASA]] is investigating the use of swarm technology for planetary mapping. A 1992 paper by [[M. Anthony Lewis (roboticist)|M. Anthony Lewis]] and [[George A. Bekey]] discusses the possibility of using swarm intelligence to control nanobots within the body for the purpose of killing cancer tumors.<ref>{{cite journal |last1=Lewis |first1=M. Anthony |last2=Bekey |first2=George A. |title=The Behavioral Self-Organization of Nanorobots Using Local Rules |journal=Proceedings of the 1992 IEEE/RSJ International Conference on Intelligent Robots and Systems |url=https://www.researchgate.net/publication/3690783}}</ref> Conversely al-Rifaie and Aber have used [[stochastic diffusion search]] to help locate tumours.<ref>{{cite journal | last1 = al-Rifaie | first1 = M.M. | last2 = Aber | first2 = A. | year = | title = Identifying metastasis in bone scans with Stochastic Diffusion Search | url =https://www.researchgate.net/publication/262223271 | journal = Proc. IEEE Information Technology in Medicine and Education, ITME | volume = 2012 | issue = | pages = 519–523 }}</ref><ref>al-Rifaie, Mohammad Majid, Ahmed Aber, and Ahmed Majid Oudah. "[http://www.academia.edu/download/30759619/Utilising-Stochastic-Diffusion-Search.pdf Utilising Stochastic Diffusion Search to identify metastasis in bone scans and microcalcifications on mammographs]." In Bioinformatics and Biomedicine Workshops (BIBMW), 2012 IEEE International Conference on, pp. 280-287. IEEE, 2012.</ref> Swarm intelligence has also been applied for [[data mining]].<ref>{{cite journal |first1=D. |last1=Martens |first2=B. |last2=Baesens |first3=T. |last3=Fawcett |title=Editorial Survey: Swarm Intelligence for Data Mining |journal=Machine Learning |volume=82 |issue=1 |pages=1–42 |year=2011 |doi=10.1007/s10994-010-5216-5 |doi-access=free }}</ref> Ant based models are further subject of modern management theory.<ref>{{cite book |last1=Fladerer |first1=Johannes-Paul |last2=Kurzmann |first2=Ernst |title=THE WISDOM OF THE MANY : how to create self -organisation and how to use collective... intelligence in companies and in society from mana. |date=November 2019 |publisher=BOOKS ON DEMAND |isbn=9783750422421}}</ref>
Category:Collective intelligence
Category:Collective intelligence
类别: 集体智慧
类别: 集体智慧
===Ant-based routing===
Category:Intelligence by type
Category:Intelligence by type
类别: 智力类型
类别: 智力类型
[[Category:Multi-agent systems]]
The use of swarm intelligence in [[Telecommunications network|telecommunication networks]] has also been researched, in the form of [[Ant colony optimization algorithms|ant-based routing]]. This was pioneered separately by Dorigo et al. and [[Hewlett Packard]] in the mid-1990s, with a number of variants existing. Basically, this uses a [[Probabilistic algorithm|probabilistic]] routing table rewarding/reinforcing the route successfully traversed by each "ant" (a small control packet) which flood the network. Reinforcement of the route in the forwards, reverse direction and both simultaneously have been researched: backwards reinforcement requires a symmetric network and couples the two directions together; forwards reinforcement rewards a route before the outcome is known (but then one would pay for the cinema before one knows how good the film is). As the system behaves stochastically and is therefore lacking repeatability, there are large hurdles to commercial deployment. Mobile media and new technologies have the potential to change the threshold for collective action due to swarm intelligence (Rheingold: 2002, P175).
Category:Multi-agent systems
Category:Multi-agent systems