Towards Understanding Modern Alchemy - Transformers as a Computational Model
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore the intricacies of in-context learning (ICL) in language models through a 37-minute lecture by Ekin Akyurek from MIT. Delve into the concept of in-context learning of formal languages (ICLL) as a model problem for understanding ICL. Examine how Transformers outperform recurrent and convolutional models in learning regular languages sampled from random finite automata. Discover the role of specialized "n-gram heads" in Transformers' superior performance and their potential to improve natural language modeling. Learn how incorporating these heads into neural models can enhance perplexity scores on datasets like SlimPajama. Gain insights into the computational capabilities of Transformers and their implications for advancing language model performance.
Syllabus
Towards Understanding Modern Alchemy
Taught by
Simons Institute
Related Courses
Natural Language ProcessingColumbia University via Coursera Developmental Robotics
University of Naples Federico II via Federica Network Dynamics of Social Behavior
University of Pennsylvania via Coursera User-centric Computing For Human-Computer Interaction
Indian Institute of Technology Guwahati via Swayam People, Networks and Neighbours: Understanding Social Dynamics
University of Groningen via FutureLearn