January 2018
Beginner to intermediate
284 pages
8h 35m
English
Neurons in a fully connected layer have full connections to all activations in the previous layer, which is different to CONV layers. In CONV layers, neurons are connected only to a local region in the input, and many of the neurons in a CONV volume share parameters. Fully connected layer is often used in the last two layers with a softmax function to replace the other activation functions to output probabilities.
Read now
Unlock full access