第682行: |
第682行: |
| ==== 人工神经网络 Artificial neural networks ==== | | ==== 人工神经网络 Artificial neural networks ==== |
| | | |
− | {{Main|Artificial neural network}}{{See also|Deep learning}}
| + | [[File:Colored neural network.svg|thumb|300px|An artificial neural network is an interconnected group of nodes, akin to the vast network of [[neuron]]s in a [[brain]]. Here, each circular node represents an [[artificial neuron]] and an arrow represents a connection from the output of one artificial neuron to the input of another.'''人工神经网络 Artificial Neural Network,ANN'''是一组相互连接的节点,类似于大脑中庞大的神经元网络。在这里,每个圆形节点代表一个人工'''神经元 Neuron''',一个箭头代表从一个人工神经元的输出到另一个输入的连接]] |
| | | |
− | [[File:Colored neural network.svg|thumb|300px|An artificial neural network is an interconnected group of nodes, akin to the vast network of [[neuron]]s in a [[brain]]. Here, each circular node represents an [[artificial neuron]] and an arrow represents a connection from the output of one artificial neuron to the input of another.]]
| |
− |
| |
− | An artificial neural network is an interconnected group of nodes, akin to the vast network of [[neurons in a brain. Here, each circular node represents an artificial neuron and an arrow represents a connection from the output of one artificial neuron to the input of another.]]
| |
− |
| |
− | '''人工神经网络 Artificial Neural Network,ANN'''是一组相互连接的节点,类似于大脑中庞大的神经元网络。在这里,每个圆形节点代表一个人工'''神经元 Neuron''',一个箭头代表从一个人工神经元的输出到另一个输入的连接
| |
− |
| |
− | Artificial neural networks (ANNs), or [[Connectionism|connectionist]] systems, are computing systems vaguely inspired by the [[biological neural network]]s that constitute animal [[brain]]s. Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules.
| |
− |
| |
− | Artificial neural networks (ANNs), or connectionist systems, are computing systems vaguely inspired by the biological neural networks that constitute animal brains. Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules.
| |
− |
| |
− | 人工神经网络,或'''连接主义系统 Connectionism System''',是计算机系统受到构成动物大脑的生物神经网络的启发后的研究成果。这种系统通过研究样本来“学习”如何执行任务,通常不需要对任何特定任务的规则进行编程。
| |
| | | |
| + | :''主文章:[[ 人工神经网络]]'' |
| + | [[人工神经网络]](ANN)学习算法,通常称为神经网络(NN),是一种受[https://en.wikipedia.org/wiki/Neural_circuit 生物神经网络]启发的学习算法。计算是根据一组相互关联的[https://en.wikipedia.org/wiki/Artificial_neuron 人工神经元]来构造的,它们使用[https://en.wikipedia.org/wiki/Connectionism 连接主义]的[https://en.wikipedia.org/wiki/Computation 计算]方法来处理信息。现代神经网络是[https://en.wikipedia.org/wiki/Non-linear 非线性][https://en.wikipedia.org/wiki/Statistical 统计][https://en.wikipedia.org/wiki/Data_modeling 数据建模]工具。它们通常用于模拟输入和输出之间的复杂关系,在数据中[https://en.wikipedia.org/wiki/Pattern_recognition 找到模式],或在观测变量之间的未知[https://en.wikipedia.org/wiki/Joint_probability_distribution 联合概率分布]中寻找统计结构。 |
| | | |
| | | |
第712行: |
第703行: |
| 人工神经网络方法的最初目标是用人类大脑解决问题的同样方式。然而,随着时间的推移,其注意力转移到执行特定的任务上,导致了与生物学的偏差。现在人工神经网络已被用于各种任务中,包括'''计算机视觉 Computer Visio'''、'''语音识别 Speech Recognition'''、'''机器翻译 Machine Translation'''、'''社会网络过滤 Social Network Filtering'''、玩棋盘和视频游戏以及医疗诊断。 | | 人工神经网络方法的最初目标是用人类大脑解决问题的同样方式。然而,随着时间的推移,其注意力转移到执行特定的任务上,导致了与生物学的偏差。现在人工神经网络已被用于各种任务中,包括'''计算机视觉 Computer Visio'''、'''语音识别 Speech Recognition'''、'''机器翻译 Machine Translation'''、'''社会网络过滤 Social Network Filtering'''、玩棋盘和视频游戏以及医疗诊断。 |
| | | |
| + | |
| + | ====深度学习==== |
| + | :''主文章:[https://en.wikipedia.org/wiki/Deep_learning 深度学习]'' |
| | | |
| | | |
第718行: |
第712行: |
| Deep learning consists of multiple hidden layers in an artificial neural network. This approach tries to model the way the human brain processes light and sound into vision and hearing. Some successful applications of deep learning are computer vision and speech recognition. | | Deep learning consists of multiple hidden layers in an artificial neural network. This approach tries to model the way the human brain processes light and sound into vision and hearing. Some successful applications of deep learning are computer vision and speech recognition. |
| | | |
− | 深度学习由人工神经网络中的多个隐层组成,通过这种方法可以尽量模拟人类大脑将光和声音处理成视觉和听觉的方式。深度学习的一些成功应用是计算机视觉和语音识别。
| + | 深度学习由人工神经网络中的多个隐层组成,通过这种方法可以尽量模拟人类大脑将光和声音处理成视觉和听觉的方式。 |
| + | |
| + | 近几年来,硬件价格的下降和个人用[https://en.wikipedia.org/wiki/Graphics_processing_unit GPU]的发展促进了深度学习概念的发展,该概念由人工神经网络中的多个隐层组成。这种方法试图模拟人脑将光和声音处理成视觉和听觉的方式。深入学习的一些成功应用是[https://en.wikipedia.org/wiki/Computer_vision 计算机视觉]和[https://en.wikipedia.org/wiki/Speech_recognition 语音识别] |
| + | <ref>Honglak Lee, Roger Grosse, Rajesh Ranganath, Andrew Y. Ng. "[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.149.802&rep=rep1&type=pdf Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations]" Proceedings of the 26th Annual International Conference on Machine Learning, 2009.</ref>。 |
| | | |
| ==== 决策树 Decision trees ==== | | ==== 决策树 Decision trees ==== |