Open AccessIMPLEMENTATION OF AUTOENCODER ON MNIST HANDWRITTEN DIGITS
Author(s) -
Ranganadh Narayanam
Publication year - 2021
Publication title -
international journal of engineering, sciences and research technology
Language(s) - English
Resource type - Journals
ISSN - 2277-9655
DOI - 10.29121/ijesrt.v10.i2.2021.5
Subject(s) - mnist database , autoencoder , pattern recognition (psychology) , computer science , artificial intelligence , dimensionality reduction , representation (politics) , encoding (memory) , artificial neural network , set (abstract data type) , curse of dimensionality , noise (video) , speech recognition , image (mathematics) , politics , political science , law , programming language
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.