IMPLEMENTATION OF AUTOENCODER ON MNIST HANDWRITTEN DIGITS

Autoencoders (AE) are a family of neural networks for which the input is the same as the output. They work by compressing the input into a latent-space representation and then reconstructing the output from this representation. The aim of an Autoencoder is to learn a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise”. In this paper De-noising Autoencoder is implemented by proposing a novel approach on MNIST handwritten digits. This model is validated through training and validation losses, and observing the reconstructed test images when comparing to the original images. The proposed model is found to be working very well.