convolutional Neural Networks

convolutional Neural Networks (convolutional neural Network): A type of classifier that uses neural networks to train parameters from data, extract features, pre-determine convolution kernel size, initialize randomly, and after feedback adjustment, different convolution cores in the training department.

convolutional layers (convolutional layer): The next layer is obtained by convolution operations on the previous layer.

Pooling layer (subsampling layers): The next layer is obtained by pooling operations on the previous layer.

convolutional Neural Network format: input layer->[[convolution layer + activation function]*m+ pooling layer *n]*k-> full-connection layer *l-> output layer

Convolution: Local feature extraction, weighted average of local data;

Convolution cores: Random initialization, adjusting parameters by training

Number of parameters: convolution core size * convolution range + Offset

Pooling: Reducing dimensions, preserving image features, and general dimensions of 2*2

Convolution can be seen as a step size of 1, pooling can be seen as a step of 2,

Local convolution, shared weights

convolutional Neural Networks