E0 270: Machine Learning, January Term 2019

E0 270: Machine Learning   (Jan-April 2019)

Department of Computer Science & Automation
Indian Institute of Science

[Course Description]  [Projects]  [Academic Honesty]  [Tutorials/Discussions]  [Schedule] 

Like last year, we will use Canvas for course management. Join the course at: https://canvas.instructure.com/enroll/XAELBR. Please use your @iisc.ac.in email address to join Canvas (if you already have an account that uses some other address, please create a new one using your @iisc.ac.in account). Candidates who join using non @iisc.ac.in accounts will be automatically removed from the course on Thursday, January 10, 2019. If you are crediting the course, it is mandatory to join Canvas. All subsequent announcements will be made only via Canvas and this page will not be updated further. Please feel free to write to [shubhamg@iisc.ac.in] if you have any queries regarding this.

Course Information

Class Meetings

Lectures: Mon-Wed 11:00am-12:30pm, CSA 117
First lecture: Wed Jan 2

Tutorial/discussion sessions will be scheduled on an on-going basis.


Prof. Ambedkar Dukkipati (ambedkar@iisc)


Shubham Gupta [shubhamg@iisc]
Tony Gracious [tonygracious@iisc]

TA Hours

Please take appointment over email from the TA

Course Description

With the increasing amounts of data being generated in diverse fields such as astronomical sciences, health and life sciences, financial and economic modeling, climate modeling, market analysis, and even defense, there is an increasing need for computational methods that can automatically analyze and learn predictive models from such data. Machine learning, the study of computer systems and algorithms that automatically improve performance by learning from data, provides such methods; indeed, machine learning techniques are already being used with success in a variety of domains, for example in computer vision to develop face recognition systems, in information retrieval to improve search results, in computational biology to discover new genes, and in drug discovery to prioritize chemical structures for screening. This course aims to provide a sound introduction to both the theory and practice of machine learning, with the goal of giving students a strong foundation in the subject, enabling them to apply machine learning techniques to real problems, and preparing them for advanced coursework/research in machine learning and related fields.

Course Evaluation (Tentative)

1 Project - 20 marks
2 Mid Term Exam - 15 marks each
1 Final Exam - 50 marks


Recommended textbooks: Additional textbooks: (Optimization texbooks)

Preferred background

E0 232: Probability and Statistics (or equivalent course elsewhere) and earned a grade of B or higher. In addition, some background in linear algebra and optimization will be helpful.


As part of the this course, you are required to work on a project. This will give you hands-on experience of working with data from various domains - text, images, videos etc that are used in the contemporary ML research, and also expose you to some specialized topics of ML that are more advanced or recent than what will be covered in the lectures.

A list of project ideas will be mailed on the mailing list. You can also come up with your own projects ideas.

Project Policy

Course Project Presentation

Title Team Members
Sensitivity Analysis on DQN Variants Renga Bashyam K G, Arun Govind M
ELMO - Deep contextualized word representations A R Shaarad, Prateek Sachan
Explainable Deep learning Anirudh Singh, Ankur Debnath, Deep Patel, Lalit Manam
Fake News
Performance Analysis on Different Approaches of Network Embedding Kishalay Das, Paarth Gupta, Kapil Pathak, Aalo Majumdar
Image Synthesis with Conditional Generative Adversarial Networks Shreya Roy, Soumyajit Gangopadhyay
BERT Arun Kanthali, Divyanshu Bhandari, Yash Patel
Graph Neural Networks Mohammed Abdul Qaathir, Koppolu Anudeep, Palakshigari Sasidhar Manjunath
Adversarially Regularized Graph Autoencoder for Graph Embeddings Abhishek Kumar, Anup Patel, Pragati Kumar Singh, Shivam Chauhan
Object Recognition in Neuromorphic images using Spiking SVM
Learning to learn by Gradient descent by Gradient descent Shrey Gupta, Aarsh Chotalia, Pratyush Menon
Mimicking Data By Learning Patterns on Data Constraints Kapil Khurana, Vishal Goel
Single Shot Object Detection in Aerial Images Mohd Haroon Ansari, Pooja Gupta, Maj. Govind
Zero Shot Recognition Using GCN Ameenudeen PE, Danish Shaikh, Deepa TM, Najath Pathiyil
Attention Based Models for Text Summarization Koushik Sen, Rahul Dev, Shah Manan Jayant, Upasana Doley
Open world Knowledge Graph Completion Bidhov Bizar,Anik Saha,Sarat Chandra,Uday Gulghane
Adversarial Training of Neural Networks for Cryptography Applications Chandrasekhar S, Nagabhushan S N, Sandesh Rao M
Neural Dialog Generation Siddharth Jha, Vinayak, Divij Mishra
Automatic Goal Generation for Reinforcement Learning Agents Nikita Parate, Ankit Wahane, Ponsuganth Ilangovan
Graph Representation Learning Nikita Yadav, Rashi Verma, Rishabh Gupta, Swyam Prakash Singh
Reinforcement Learning: Policy gradient and TRPO Dhiraj Shanbhag, Ashish Raghuvanshi, Waquar Azam
Deep Generative Models with focus on StackGAN Gururaj K, Sakya Basak, Rahul Bansal, Rajat Nagpal
Spectral Clustering Tapesh Yadav
Transformer Network for Abstractive Text Summarization Aniruddha Bala, Chittersu Raghu, Ravi Raj Saxena
Unsupervised Abstractive Text Summarization Aadesh Magare, Nilesh Kande, Rishabh Meshram, Shubham Sharma

Academic Honesty

As students of IISc, we expect you to adhere to the highest standards of academic honesty and integrity.

Elements of the course are designed to support your learning of the subject. Copying will not help you (in the exams or in the real world), so don't do it. If you have difficulties learning some of the topics or lack some background, try to form study groups where you can bounce off ideas with one another and try to teach each other what you understand. You're also welcome to talk to any of us and we'll be glad to help you.

If any exam/report is found to be copied, it will automatically result in a zero grade for that exam/project and a warning note to your advisor. Any repeat instance will automatically lead to a failing grade in the course.


Will be updated later