Professor Danish Pruthi is offering weekend lectures on large language models, starting on 8 March 2025, on three consecutive Saturdays. All are welcome to attend the lectures! Registration is mandatory. The details are as follows.
Description of the course: A Gentle Introduction to Large Language Models
We interact with language models and derivates, such as ChatGPT, on a daily basis (at times, unknowingly). Such models answer the questions we ask, autocomplete words we are likely to type, help translate text from languages we don’t know, and most importantly, complete our assignments and homework. This short course will gently introduce language models, starting with N-gram models building all the way up to transformers, and how they are pre-trained and aligned to be safe.
- Module 1: N-gram language models
- Module 2: Recurrent neural networks
- Module 3: Transformers
- Module 4: Pre-training
- Module 5: Post-training and alignment
Date and time:
08 March 2025 (10:00-11:30 AM and 12:00-01:30 PM)
15 March 2025 (10:00-11:30 AM and 12:00-01:30 PM)
22 March 2025 (10:00-11:30 AM)
Venue: #102, Department of Computational and Data Sciences, IISc/online
Registration form: https://forms.office.com/r/SE8iVzHaPm
Biography of the instructor: Danish Pruthi is an Assistant Professor at the Indian Institute of Science (IISc), Bengaluru. He received his PhD from the School of Computer Science at Carnegie Mellon University. He is broadly interested in the areas of natural language processing (NLP) and deep learning, with a focus towards inclusive development and evaluation of AI models. He completed his Bachelor’s degree in Computer Science from BITS Pilani, Pilani. He is also a recipient of the Schmidt Sciences AI2050 Early Career Fellowship, Siebel Scholarship, CMU Presidential Fellowship, and industry awards from Google and Adobe Inc. Until recently, his legal name was only Danish—an ‘edge case’ for many deployed NLP systems, leading to airport quagmires and, in equal parts, funny anecdotes.
