卷积神经网络网络架构计算_软计算中的神经网络架构

卷积神经网络网络架构计算

Artificial Neural Network is defined as a data processing system consisting of a large number of simple highly interconnected processing elements called neurons inspired from the brain. Generally, an Artificial Neural Network structure can be represented using a directed graph.

人工神经网络被定义为一种数据处理系统，它由大量简单的高度互连的处理元件组成，这些处理元件被称为“大脑神经元”。 通常，可以使用有向图来表示人工神经网络结构 。

Diagraph is used in ANN as the neural system is restricted to flow in a specific direction.
A graph is an ordered 2 tuple (V, E) consisting set of vertices and set E of edges.

由于神经系统被限制在特定方向上流动，因此在神经网络中使用了Diagraph。
的曲线图是一个有序的2元组(V，E)，其由顶点和边的集合E的组。

网络架构的类别 (Classes of network architecture)

1. Single layer feedforward network

   单层前馈网络

2. Multi-layer feedforward network

   多层前馈网络

3. Recurrent network

   循环网络

1)单层前馈网络 (1) Single layer feedforward network)

• This type of network comprises two layers, namely the input layer and output layer.

  这种类型的网络包括两层，即输入层和输出层。

• Input layer neurons receive the input signals and output layer neurons receive the output signal.

  输入层神经元接收输入信号，而输出层神经元接收输出信号。

• The synaptic links carrying the weight connect every input neurons to output neurons but not vice-versa.

  负重的突触链接将每个输入神经元连接到输出神经元，反之则不然。

• This type of network is also called feedforward in type or acyclic in nature.

  这种类型的网络在本质上也称为前馈或非循环。

• The output layer alone which performs computations so is also called a single-layer network.

  单独执行计算的输出层也称为单层网络。

• The input layer sends the signals to the output layer thus the name of the feedforward network.

  输入层将信号发送到输出层，即前馈网络的名称。

2)多层前馈网络 (2) Multi-layer feed forward network)

• It comprises multiple layers.

  它包括多层。

• This type of architecture besides processing an input and output layer.

  这种类型的体系结构除了处理输入和输出层。

• This second class of feedforward network distinguishes itself by the presence of one more hidden layer, whose computational nodes are corresponding called hidden neurons or hidden units.

  第二类前馈​​网络通过一个隐蔽层的存在来区分自己，该隐蔽层的计算节点相应地称为隐蔽神经元或隐蔽单元。

• Hidden layer neurons are present between the input layer and the output layer.

  隐藏层神经元存在于输入层和输出层之间。

• Hidden layer help in performing useful intermediary computations before directing the input to the output layer.

  隐藏层有助于在将输入定向到输出层之前执行有用的中间计算。

• Multilayer feed-forward network with L input neurons, m1 neurons in the first hidden layer,m2 neurons in the second layer and n output can be written as: L-m1-m2-n

  具有L个输入神经元，第一个隐藏层中的m1个神经元，第二个层中的m2个神经元和n个输出的多层前馈网络可以写为： L-m1-m2-n

• These networks differ from feedforward architecture in the sense that there is at least one feedback loop.

  这些网络在至少有一个反馈回路的意义上与前馈体系结构不同。

• There could also be neurons with self-feedback links, that is the output of neurons is feedback into itself as input

  也可能存在具有自我反馈链接的神经元，即神经元的输出被反馈到自身作为输入

3)经常性网络 (3) Recurrent Network)

• These networks differ from feedforward architecture in the sense that there is at least one feedback loop.

  这些网络在至少有一个反馈回路的意义上与前馈体系结构不同。

• These networks exist one layer with feedback connections.

  这些网络存在具有反馈连接的一层。

• There could also be neurons with self-feedback links, that is the output of neurons is feedback into itself as input.

  也可能存在具有自我反馈链接的神经元，即神经元的输出作为输入反馈到自身中。

翻译自: https://www.includehelp.com/soft-computing/neural-network-architecture.aspx

卷积神经网络网络架构计算