Measuring Performance of Generative Adversarial Networks on Devanagari Script
This work addresses the challenge of measuring GAN performance for a specific domain (Devanagari script), but it is incremental as it adapts existing methods to new data without major methodological innovations.
The paper tackled the problem of evaluating Generative Adversarial Networks (GANs) by applying them to the Devanagari script, which has a more complex structure than standard datasets like MNIST, and achieved results assessed using three custom-built classifiers.
The working of neural networks following the adversarial philosophy to create a generative model is a fascinating field. Multiple papers have already explored the architectural aspect and proposed systems with potentially good results however, very few papers are available which implement it on a real-world example. Traditionally, people use the famous MNIST dataset as a Hello, World! example for implementing Generative Adversarial Networks (GAN). Instead of going the standard route of using handwritten digits, this paper uses the Devanagari script which has a more complex structure. As there is no conventional way of judging how well the generative models perform, three additional classifiers were built to judge the output of the GAN model. The following paper is an explanation of what this implementation has achieved.