Figure 2 illustrates an exemplary
convolutional neural network layers 200 in more detail. An example
subregion of the input layer region 204 of an
input layer region 202 region of an image is analyzed by a set of
convolutional layer subregion 208 in the
convolutional layer 206. The
input layer region 202 is 32x32 neurons long and wide (e.g., 32x32 pixels), and three neurons deep (e.g., three color channels per pixel). Each neuron in the
convolutional layer 206 is connected only to a local region in the
input layer region 202 spatially (in height and width), but to the full depth (i.e. all color channels if the input is an image). Note, there are multiple neurons (5 in this example) along the depth of the
convolutional layer subregion 208 that analyzes the
subregion of the input layer region 204 of the
input layer region 202, in which each neuron of the
convolutional layer subregion 208 may receive inputs from every neuron of the
subregion of the input layer region 204.