Using autoencoders to reconstruct handwritten digit images

An autoencoder is a neural network whose purpose is to code its input into small dimensions, and for the result that is obtained to be able to reconstruct the input itself. Autoencoders are made up by the union of the following two subnets: encoder and decoder. A loss function is added to these functions and it is calculated as the distance between the amount of information loss between the compressed representation of the data and the decompressed representation. The encoder and the decoder will be differentiable with respect to the distance function, so the parameters of the encoding and decoding functions can be optimized to minimize the loss of reconstruction, using the gradient stochastic.

Getting ready

...