Why The Hype Around GANs


  • Machine Learning

  • Image Processing


Mentors :

  • Akshit Shrivastava
  • Tezan Sahu

Mentees :

  • Aakriti
  • Atin Bainada
  • Chirag Garg
  • Liza Dahiya
  • Samyak Shah
  • Sumit Jain
  • Thomas Jacob
  • Yash Gadhia
  • Yatharth Champaneria


Yann LeCun described GANs as “the most interesting idea in the last 10 years in Machine Learning”. And, indeed, Generative Adversarial Networks (GANs for short) have had a huge success since they were introduced in 2014 by Ian J. Goodfellow.

This project will involve learning many machine learning algorithms leading to GANs. Mentees will implement a Generative Adversarial Network from scratch.

For students who have participated in Summer of Science (Machine Learning track) before, this would be a great hands-on project!

Tentative Timeline :

Week Work
Week 1-2 Learn/Brush-up Python, Torch, Jupyter, Numpy, Unix commands
Week 3-4 Learn Linear Regression, Logistic Regression, Neural Networks
Week 5-6 Read up on the use cases and building blocks of Deep Learning.
Week 7-8 Implement a generative adversarial network from scratch and train it on toy dataset.
Week 9-10 Learn PyTorch/TensorFlow, implement a GAN network using the library.
Week 11-12 Start collecting data and training. Document all interesting observations