International Journal For Multidisciplinary Research

E-ISSN: 2582-2160     Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 6 Issue 6 November-December 2024 Submit your research before last 3 days of December to publish your research paper in the issue of November-December.

A practical Approach to Handwritten Digit Generation with Generative Adversarial Networks on MNIST

Author(s) S.K.ABHYUDHY, SAVITHA.C, KAREEM KHAN
Country India
Abstract Implementation of a Generative Adversarial Network (GAN) utilizing the MNIST (Modified National Institute of Standards and Technology database) dataset of handwritten digits, the GAN comprises a generator creating synthetic images from random noise and a discriminator to classifying these images as real or fake. The Generator utilizes leaky ReLU (rectified linear unit) activations, Batch normalization and reshaping to produce 28x28 grayscale images, while the Discriminator uses dense layers, leaky ReLU, and dropout to enhance classification accuracy. Both networks are trained using the Adam optimizer to improve stability and performance. The GAN is trained in an adversarial setup where the Generator seeks to create convincing images and the Discriminator aims to correctly classify them. Results demonstrate the GAN's ability to generate high-quality handwritten digit images, displaying its effectiveness and providing valuable insights into best practices for GAN implementation and training.
Keywords Handwritten Digit Generation, Neural Networks, Image Synthesis, batch normalization, Adam Optimizer, Generative Modelling
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 6, Issue 6, November-December 2024
Published On 2024-11-05
Cite This A practical Approach to Handwritten Digit Generation with Generative Adversarial Networks on MNIST - S.K.ABHYUDHY, SAVITHA.C, KAREEM KHAN - IJFMR Volume 6, Issue 6, November-December 2024.

Share this