CNN Receptive Field, How Neural Networks See. In Convolutional Neural Networks (CNNs), the receptive field refers to the region of the input image that a particular neuron works with. It is equal to the maximum area that the network can process It represents the portion of the image the neuron "sees" when making its computation. As layers stack in a CNN, the receptive field expands, allowing deeper layers to capture more complex patterns from larger sections of the image | Md Ismail Sojal