流态机

来自集智百科 - 复杂系统|人工智能|复杂科学|复杂网络|自组织
跳到导航 跳到搜索

此词条由神经动力学模型读书会词条梳理志愿者1210080212翻译审校，未经专家审核，带来阅读不便，请见谅。

A liquid state machine (LSM) is a type of reservoir computer that uses a spiking neural network. An LSM consists of a large collection of units (called nodes, or neurons). Each node receives time varying input from external sources (the inputs) as well as from other nodes. Nodes are randomly connected to each other. The recurrent nature of the connections turns the time varying input into a spatio-temporal pattern of activations in the network nodes. The spatio-temporal patterns of activation are read out by linear discriminant units.

A liquid state machine (LSM) is a type of reservoir computer that uses a spiking neural network. An LSM consists of a large collection of units (called nodes, or neurons). Each node receives time varying input from external sources (the inputs) as well as from other nodes. Nodes are randomly connected to each other. The recurrent nature of the connections turns the time varying input into a spatio-temporal pattern of activations in the network nodes. The spatio-temporal patterns of activation are read out by linear discriminant units.

液体状态机(LSM)是一种使用脉冲神经网络的一类储备池计算机。一个LSM 由大量单元的集合(称为节点或神经元)组成。每个节点接收来自外部源(输入)以及其他节点的时变输入。节点之间是随机连接的。循环连接本质上将时变的输入变成网络节点激活函数的时空模式。激活的时空模式由线性判别单元读出。

The soup of recurrently connected nodes will end up computing a large variety of nonlinear functions on the input. Given a large enough variety of such nonlinear functions, it is theoretically possible to obtain linear combinations (using the read out units) to perform whatever mathematical operation is needed to perform a certain task, such as speech recognition or computer vision.

The soup of recurrently connected nodes will end up computing a large variety of nonlinear functions on the input. Given a large enough variety of such nonlinear functions, it is theoretically possible to obtain linear combinations (using the read out units) to perform whatever mathematical operation is needed to perform a certain task, such as speech recognition or computer vision.

这些循环连通的节点最终将计算输入基础上的许多非线性函数。给定足够多的这种非线性函数，理论上可以获得线性组合(使用读出单元)来执行完成某项任务所需的任何数学运算，如语音识别或计算机视觉。

The word liquid in the name comes from the analogy drawn to dropping a stone into a still body of water or other liquid. The falling stone will generate ripples in the liquid. The input (motion of the falling stone) has been converted into a spatio-temporal pattern of liquid displacement (ripples).

The word liquid in the name comes from the analogy drawn to dropping a stone into a still body of water or other liquid. The falling stone will generate ripples in the liquid. The input (motion of the falling stone) has been converted into a spatio-temporal pattern of liquid displacement (ripples).

这个名字中的“液体”一词来源于将一块石头投入静止的水体或其他液体的类比。落下的石头会在液体中产生波纹。输入(落石的运动)被转换成液体位移(波纹)的时空模式。

LSMs have been put forward as a way to explain the operation of brains. LSMs are argued to be an improvement over the theory of artificial neural networks because:

LSMs have been put forward as a way to explain the operation of brains. LSMs are argued to be an improvement over the theory of artificial neural networks because:

液体状态机已被提出作为解释大脑运作的一种方法。有人认为，液体状态机是对人工神经网络理论的改进，因为:

  1. Circuits are not hard coded to perform a specific task.
  2. Continuous time inputs are handled "naturally".
  3. Computations on various time scales can be done using the same network.
  4. The same network can perform multiple computations.
  1. Circuits are not hard coded to perform a specific task.
  2. Continuous time inputs are handled "naturally".
  3. Computations on various time scales can be done using the same network.
  4. The same network can perform multiple computations.
  1. 电路没有硬编码来执行特定任务。
  2. 连续的时间输入被很自然地处理。
  3. 使用同一个网络可以进行不同时间尺度的计算。
  4. 同一个网络可以执行多个计算。

Criticisms of LSMs as used in computational neuroscience are that

  1. LSMs don't actually explain how the brain functions. At best they can replicate some parts of brain functionality.
  2. There is no guaranteed way to dissect a working network and figure out how or what computations are being performed.
  3. Very little control over the process.

Criticisms of LSMs as used in computational neuroscience are that

  1. LSMs don't actually explain how the brain functions. At best they can replicate some parts of brain functionality.
  2. There is no guaranteed way to dissect a working network and figure out how or what computations are being performed.
  3. Very little control over the process.

液体状态机在计算神经科学中的评价：

1.液体状态机并不能真正解释大脑是如何运作的，他们最多只能复制部分大脑功能。

2.没有一种可靠的方法来分析一个工作网络，并弄清楚正在执行的计算是如何执行的或执行的是什么。

3.对整个过程几乎没有控制。

Universal function approximation

If a reservoir has fading memory and input separability, with help of a readout, it can be proven the liquid state machine is a universal function approximator using Stone–Weierstrass theorem.[1]

If a reservoir has fading memory and input separability, with help of a readout, it can be proven the liquid state machine is a universal function approximator using Stone–Weierstrass theorem.

= = 万能函数逼近 = =

如果一个储备池具有记忆衰退和输入分离性，借助读出器，可以用 Stone-Weierstrass 定理证明液体状态机是万能函数逼近器。

See also

  • Echo state network: similar concept in recurrent neural network
  • Reservoir computing: the conceptual framework
  • Self-organizing map

= = = =

  • 回声状态网络: 循环神经网络中的类似概念
  • 储备池计算: 概念框架
  • 自组织映射

Libraries

  • LiquidC#: Implementation of topologically robust liquid state machine [2] with a neuronal network detector [1]
  • LiquidC#: Implementation of topologically robust liquid state machine with a neuronal network detector

= =

  • LiquidC # : 用神经元网络探测器[2]实现拓扑鲁棒的液体状态机[2]

References

  1. ↑ Maass, Wolfgang; Markram, Henry (2004), "On the Computational Power of Recurrent Circuits of Spiking Neurons", Journal of Computer and System Sciences, 69 (4): 593–616, doi:10.1016/j.jcss.2004.04.001
  2. ↑ 2.0 2.1 Hananel, Hazan; Larry, M., Manevit (2012), "Topological constraints and robustness in liquid state machines", Expert Systems with Applications, 39 (2): 1597–1606, doi:10.1016/j.eswa.2011.06.052.{{citation}}: CS1 maint: multiple names: authors list (link)



Category:Artificial neural networks

类别: 人工神经网络


This page was moved from wikipedia:en:Liquid state machine. Its edit history can be viewed at 流态机/edithistory

取自“https://wiki.swarma.org/index.php?title=流态机&oldid=31651”