Neural network includes convolution layer. What other layers are there?

1, ConvolutionalNeuralNetwork (CNN) is a kind of feedforward neural network, and its artificial neurons can respond to the surrounding units in a part of coverage, which has excellent performance for large-scale image processing.

2. The basic structure of convolutional neural network consists of the following parts: input layer, convolution layer, pool layer, activation function layer and full connection layer.

3. At present, convolutional neural networks are generally feedforward neural networks formed by overlapping convolution layer, convergence layer and fully connected layer, and are trained by back propagation algorithm. Convolutional neural network has three structural characteristics: local connection, weight sharing and convergence.