CSE Department Special Modules courses in 2021 Holi Semester

In the Holi Term 2021, the CSE Department is offering four 1-credit Special Modules. These may not have listed pre-requisites in the Courses of Study, but it is expected that if you wish to register for any of these courses, you will have the necessary background and maturity. In particular, these courses are meant for those seeking to do research (PhD, MS Research, and M Tech level students), so the expectation will be that you have competed 120 earned credits. These courses only count for OE credits for undergrads, but are PE credits for Dual-degree, M Tech, MS R aand PhD students. Do NOT register for this course to complete your credit requirements.

All students wishing to register for any Special Modules Courses are required to fill the following form:
Choice for Special Modules COV8xx (Holi Term 2021)

Students are not allowed to register for more than 1 special module. Instructors reserve the right to deregister those who do not fill this form. Also, if you are opting for a Special Module, you will be required to take it for credit (exception given only to PhD students), and you will be expected not to withdraw (the only concession being on grounds of medical or family emergencies).

COV878 Special Module in Machine Learning: Meta-Learning

Instructor: Prof. Gautam M Shroff, TCS Research

(Email gautam.shroff @ tcs.com)


About the Course: ‘Meta-Learning’ or ‘learning to learn’ refers to the problem of developing machine learning/deep learning models that can adapt to new tasks/domains/environments, either very “rapidly”, i.e., requiring very little new data/experience, or in a manner robust to distributional shifts, such as when users change their behaviour, as has been experienced across the board due to the pandemic. Both scenarios are also closely related, since distributional shifts also imply the relative scarcity of ‘new’ data, with practical considerations making it imperative to rapidly adapt to every ‘new normal’. Meta-learning is also closely related to two long-desired goals of AI in general, viz., continual learning (without forgetting) and learning higher-level (and ideally causal) representations that allow for better generalisation, e.g. to deal with non-stationarity or for longer duration forecasting etc.

In the light of the above context, the course will aim to (i) cover the basic techniques for meta-learning (ii) outline and model selected industry applications in a meta-learning setting and (iii) highlight the connections with closely related long-term AI-research goals.

Lectures (live but online):

  1. Basics of Meta-learning: Metric/Model/Optimisation-based - 3 hours
  2. Meta-Learning for Transfer, Concept-drift, Continual learning and Reinforcement Learning - 3 hours
  3. Learning from almost No Data: Meta-interpretive Program Synthesis - 2 hours
  4. Selected applications of Meta-learning in E-commerce, Advertising and Finance - 3 hours
  5. Causality, Disentangled Representations and Causal Reinforcement Learning - 3 hours

Evaluation: online MCQ exam based on lectures and prescribed readings (papers) and viva (10 min).

COV882 Special Module in Software Systems: Software Security Verification

Instructor: Prof. Karthik Bhargavan

The goal of the course is to teach students how to use formal verification tools to analyze the design and implementation of security mechanisms, with a focus on real-world cryptographic protocols.

At the end of the course, students can expect to be familiar with modern cryptographic protocols and three state-of-the-art tools, and have some hands-on experience in using these tools.



Evaluation will be done on the basis of verification exercises and a longer verification project.

COV885 Special Module in Computer Applications: Creating Accessible Documents for Visually Impaired

Course level: PG - Senior and Research

Instructor: Prof. Volker Sorge and Prof. M. Balakrishnan

Discipline: Information Technology

Lecture hours: 14 Hours

Pre-requisites: Programming, Data Structures

Course Description: Persons with visual impairments are still underrepresented due to inaccessibility of the STEM (Scientific, Technical, Engineering, and Mathematical) content. STEM document contains a number of artefacts like table, equations, diagrams, data visualization, etc. that remain inaccessible as screen readers have primarily focused on plain text. This course will focus on conversions of various artefacts from inaccessible formats to accessible formats. Here, accessibility means access to persons with visual impairments with assistive technologies like screen reader.

Syntactic and semantic analysis are required for the accessibility of the tables and equations. Syntactic analysis is required to understand the mathematical relations between the different variables of the equation. On the other hand, semantic analysis is required to adapt the audio rendering on the basis of the context to minimize the verbosity and cognitive load. Further, individual user specific adaptations are required to enhance effectiveness as well as efficiency of audio rendering. Such adaptations should be based on the individual user’s experience with audio rendering as well as familiarity with the content.

Course Contents

Topic Contents # of hours
Introduction STEM Documents and their features 2
Document sources Retro-digitized, born digital and born accessible 2
Formats and conversion Physical(paper) and digital and associated conversion challenges 2
Semantics Representation,generation and recovery techniques 2
Physical and other accessibility techniques Braille, tactile, audio-tactile and haptics 2
Electronic accessibility Screen reading, interaction & sonification 2
Personalization Adaptations including impairment specific and localization 2

Lab component

There would be a supplementary laboratory component. Details are available at http://progressiveaccess.com/empower18/

This would expose the students to creating accessible equations, chemistry diagrams, physics diagrams and statistics. On the whole focus would be on generating accessible diagrams.

Software tools & resources:


Mainly research papers – key conferences ICCHP and CSUN

Thesis of Dr. T.V. Raman, ACM Dissertation Award, Cornell University, 1994

COV888 Special Module in Database Systems: Web Data Management

Instructor: Prof. Subhash Bhalla, Aizu University, Japan

(Email: bhalla2310 @ gmail . com)

Assignments (1): Laboratory exercises and homework (10 marks)

Final Grade(2): Minor I, II (20 marks each): Total: (1)+(2)=50


  1. Distributed Systems, Coulouris, Addison-Wesley
  2. Guide to Reliable Distributed Systems, Ken Birman, Springer.
  3. Database Systems Concepts, Silberschatz et al.
  4. Readings - Materials/References discussed in classes

Lectures (tentative schedule):

  1. Edge Computing (P2P Systems)
  2. Semi-structured and unstructured Data
  3. Datasets in Polystore Systems
  4. Set Theoretic Query Languages for web data
  5. ADTs and languages (ADL,JSON,KML,XML,.. SPARQL)
  6. Web Services in Service-Oriented Architecture (SOA)
  7. Asynchrony in peer-to-peer (P2P) transactions
  8. Quiz 1
  9. Distributed Systems
  10. Extending Blockchains in P2P Computing
  11. Workflows in Polystore Data Management
  12. Business Transactions
  13. Final Class QUIZ 2, Deadline: Submit assignments
  14. Final Class Meeting