Variational-DL

Variational Deep Learning is a method of deep learning where we use Neural Networks to generate data, instead of drawing conclusions from it.

We have currrently implemented the following Autoencoders and Generative Adversarial Networks:

• [x] Vanilla Autoencoder
• [x] Denoising Autoencoder
• [x] Sparse Autoencoder
• [x] Contractive Autoencoder
• [x] Variational Autoencoder
• [x] Deep Convolutional Generative Adversarial Network
• [x] Conditional Generative Adversarial Network

All the models have been benchmarked on the MNIST dataset.

Contributors:

• Pulkit Mathur
• Atharva Kathale
• Appari Shanti
• Sibam Parida
• Sushant Jha
• Vignesh Srinivas
• Kalyani Sainis
• Rishika Bhagwatkar
• Khurshed Fitter
• Saketh Bachu
• Siddharth Singh