Assignment can be found here. Join the Slack workspace here.

Dates: 20th - 21st December. Website.

SAiDL's Season of Code gives students to work on cutting-edge AI projects with a strong focus on Open Source. Find the details of this year's project here.

Assignment can be found here. Join the Slack workspace here.

Dates: 22nd - 24th November. Website.

Assignment can be found here. Join the Slack workspace here.

Assignment can be found here. Join the Slack workspace here.

Dates: 25th - 26th November. Website.

SAiDL's Season of Code gives students to work on cutting-edge AI projects with a strong focus on Open Source. This year's projects: 1) Meta-Learning with JAX, 2) Event Vision Library, 3) Exploring Deep Learning models for Visual Saliency Prediction. More information here.

Dates: 18th April - 27th April, 2022. Website. Details here.

Speakers: Omatharv Vaidya, Vedant Shah, Sharad Chitlangia, Rajaswa Patil, Alish Dipani. Slides.

Assignment can be found here. Join the Slack workspace here.

Dates: 2nd & 3rd October, 2021. Website. Session recordings.

Taught by: Sharad Chitlangia, Vedant Shah, Rishabh Patra, Soundarya Krishnan, Ishita Mediratta, Anmol Agarwal.

Taught by: Vishwa Shah, Shrey Pandit, Hrithik Nambiar, Yash Bhartia, Sushmit Wani.

SAiDL's Season of Code gives students to work on cutting edge AI projects. This year's projects: 1) Causal Inference in Time Series, 2) Program Synthesis with Julia, 3) Visualisation Library for Vision Transformers, 4) Meta Learning with Jax. More information here.

Assignment can be found here.

Dates: 25th & 26th July, 2020. Website. Session recordings.

Assignment can be found here.

Projects: 1) Adversarial NLP, 2) Deep Contextual Bandits, 3) Computer Vision for Sports Analytics, 4) Knowledge Distillation library, 5) Twitter Feed Distillation, 6) Benchmarking Causal inference and RL, 7) Deep Learning for Time Series, 8) Spiking Neural Networks. More information here.

A Quark Summer Project on learning the fundamentals of deep learning and how they are applied in Computer Vision, Natural Language Processing and Reinforcement Learning.

Assignment can be found here.

Taken by Rajaswa Patil and Pranav Mahajan. The course included introduction to fundamental concepts of Machine Learning and Deep learning and hands-on experience through projects and self-organized Kaggle competitions. Batch strength: 120 students. Course handout.

Course taken by Ashwin Vaswani, Rijul Ganguly. Course handout.

Learning to play games with RL, Computer Vision, Financial Market Modelling, Machine Learning and AI & Cognitive Neuroscience.

Assignment can be found here.

Taken by Mehul Rastogi, Sharad Chitlangia, Rijul Ganguly and Ajay Subramanian. Slides and resources can be found here.

Assignment can be found here.

Taken by Alish Dipani, Mehul Rastogi, Sharad Chitlangia, Rijul Ganguly. Slides and resources can be found here.

Induction assignment.