Teaching
I have served as Assisting/Co-Instructor for several Masters level courses and Undergraduate Level courses at TU Delft during my PostDoc and IIIT-Delhi during my PhD.
CSE2525 Data Mining
Level: Bachelors
Teaching Assistant to: Avishek Anand, Sicco Verwer, Nergin Tömen
This course introduces students to the fundamental concepts and techniques of data mining. Topics include data preprocessing, probabilistic counting, dimensionality reduction, clustering, anomaly detection, and mining text and graph data. The course also includes practical sessions where students apply these techniques using popular data mining tools and software. My duties involved designing of assignments, holding office hours to clarify queries on assignments and projects.
DSAIT4050 Information Retrieval
Level: Masters
Co-taught with: Avishek Anand, Sole Pera, Jie Yang
In this course, students explore the principles and practices of information retrieval. The syllabus covers the design and implementation of search engines, text indexing, query processing, and evaluation of information retrieval systems. Special topics include learning-to-rank, neural ranking models, and recommender systems. I delivered several lectures on RAG systems for QA tasks.
CS4360 Natural Language Processing (NLP)
Level: Masters
Co-taught with: Avishek Anand, Jie Yang
This course delves into the field of Natural Language Processing, covering both the theoretical and practical aspects. Students learn about text processing, language modeling, syntactic and semantic analysis, and large-language models. The course emphasizes hands-on projects and applications of NLP techniques in real-world scenarios.
Past Courses (@IIIT-Delhi)
2021 - 2022: Data Mining
Level: Bachelors and Masters
Teaching Assistant to: Vikram Goyal
Course Description: Data mining aims at finding the useful patterns in large data sets. Interest in the field is motivated by the growth of computerized data collection due to ubiquity of Internet enabled devices. This course will cover a set of techniques designed to be used for finding interesting patterns from the data. The techniques include classification, clustering, association rule minin and sequence mining. Students will learn and use the open source R statistical software, see http://www.r-project.org, and machine learning packages such as Weka in this course
2021 - 2022: Big Data Analytics
Level: Bachelors and Masters
Teaching Assistant to: Vikram Goyal
Course Description: Distributed processing frameworks have emerged as a feasible and cost effective way of analyzing the increasing volume of data. This course provides a solid understanding of two of the most popular of distributed processing frameworks - Hadoop and a more recent incarnation called Spark. Examples and hands-on exercises will prepare those taking this course to be able to apply these frameworks in practice.