Agenda

Week 1: Mathematics and Basic Methods in ML

Day
Workshop
15th June, 5:00-6:30 PM
Watch on YouTube		 Linear Algebra, Probability and Statistics
Pramit Das
1st Year PhD, University of Michigan

Prerequisites:We expect participants to have knowledge equivalent to a freshman level course on Linear Algebra. Familiarity with Python, Jupyter notebooks and Anaconda will also help greatly. Beginners are encouraged to go through the following resources we have provided in the past: Resources: You can find the jupyter notebook used by Pramit on our GitHub. Thank you to Mustafa and Nirjhar for explaining everything wonderfully, and of course Pramit for giving an excellent tour of the math behind ML. Abstract:

We plan to learn the fundamental uses of Eigenvalues, matrix factorization, and how we use those notions in ML. In the second part, we intend to go over some basic statistical distributions and a very simple yet useful technique called Naive Bayes Classification.

16th June, 5:00-6:30 PM
Watch on YouTube		 Linear Regression and Multi-Variable Calculus
Aman Bhardwaj
2nd Year MS(Research), CSE IIT Delhi

Reference Resources:Please go through the prerequisites of the previous session in case you are not familiar with Python, Jupyter and libraries. For this session:
  • GitHub Repo Link - One-Stop destination for everything you'll need.
  • Jupyter Notebook - Aman has prepared a wonderful notebook to illustrate what he will teach today. The link to this is also present in the GitHub Repo of the previous point.
  • Aman has also been kind enough to create a separate repository dedicated to his session today. You can find it by clicking here and it is also present in our repo.
  • P.S. - These resources are really amazing, make sure you go through them:) And thank you to Aman for creating them!
Abstract:

Aman will broadly be covering the following topics:

  1. Introduction to ML, its types and important general concepts such as overfitting
  2. A tour of Multi-Variable Calculus, starting from scalars through Gradients, Convexity and ending with applications
  3. Linear Regression - Basics, Algorithm and hands-on Demo.

Week 2: Deep Learning and its Applications

Day
Workshop
22nd June, 5:00-6:30 PM Introduction to Deep Learning
Ananye Agarwal
4th Year B.Tech, CSE IIT Delhi

Abstract:

Ananye will be starting with a brief tutorial on Logistic Regression, and will then move on to Deep Learning. He will talk about the motivation behind it and fundamental concepts of Neural Nets, followed by a hands-on introduction to Pytorch.

23rd June, 5:00-6:30 PM Introduction to Convolutional and Recurrent Neural Nets
Jay Paranjape
4th Year B.Tech, CSE IIT Delhi

Abstract:

Computer Vision and Natural Language Processing are two of the most studied areas of Deep Learning. Computer Vision is used in various fields like Medical imaging, automatic driving and so on. Similarly, NLP is used in chatbots, recommendations, world understanding and so on. This talk will take you a bit deeper into what makes the computer understand images or text - CNNs and RNNs. Get to know more about these building blocks how they have been crucial to Machine Learning over the years and we hope you will be using them in your own projects soon enough.

Week 3: Mega Hackathon

Week 4: More Methods in Machine Learning

Day
Workshop
3rd July, 5:00-6:30 PM More Methods in Machine Learning
Anshul Mittal
2nd Year Google PhD Fellow, CSE IIT Delhi

Abstract:

Anshul will be covering some interesting traditional ML Methods. The algorithms to be discussed include Gaussian Discriminant Analysis, K-Means and Expectation-Maximization. This will serve to give an idea of the diversity in ML Methods, beyond Regression and Deep Learning.