Error Bounds for Approximations Using Multichannel Deep Convolutional Neural Networks with Downsampling

Figure 2

Illustration of MDCNNs with downsampling: the input data has channels; then, the multichannel convolution is acted on the input data with filters, and the output of the first layer contains channels; next, the multichannel convolution is acted on the outputs of the first layer with filters following by a downsampling operator, and the output of the second layer contains channels; and so on.