The convolution operator allows filtering an input signal in order to extract some part of its content. Autoencoders in their traditional formulation do not take into account the fact that a signal can be seen as a sum of other signals. Convolutional Autoencoders, instead, use the convolution operator to exploit this observation. They learn to encode the input in a set of simple signals and then try to reconstruct the input from them.
Introduction to Autoencoders
Autoencoders are neural networks models whose aim is to reproduce their input: this is trivial if the network has no constraints, but if the network is constrained the learning process becomes more interesting.
First blog post. Nothing more than a greeting