Visualizing transformers and attention | Talk for TNG Big Tech Day ’24

This is CS50, Harvard University’s introduction to the intellectual enterprises of computer science and the art of programming. TABLE OF CONTENTS 00:00:00 – Welcome00:01:01 – Introduction00:03:13 – Image Generation00:08:23 – ChatGPT00:11:06 – Prompt Engineering00:12:40 – CS50.ai00:19:03 – Generative AI00:22:08 – Decision Trees00:26:33 – Minimax00:34:27 – Machine Learning00:42:56 – Deep Learning00:48:53 – Large Language Models00:53:36 –…

LangChain became immensely popular when it was launched in 2022, but how can it impact your development and application of AI models, Large Language Models (LLM) in particular. In this video Martin Keen shares an overview of the features and uses of LangChain.

In a society that is confronting the new age of AI in which LLMs begin to display aspects of human intelligence, understanding the fundamental theory of deep learning and applying it to real systems is a compelling and urgent need. This panel will introduce some new simple foundational results in the theory of supervised learning….

This is the second of a series of 3 videos where we demystify Transformer models and explain them with visuals and friendly examples. 00:00 Introduction01:18 Recap: Embeddings and Context04:46 Similarity11:09 Attention20:46 The Keys and Queries Matrices25:02 The Values Matrix28:41 Self and Multi-head attention33:54: Conclusion

If you’re interested in the herculean task of interpreting what these large networks might actually be doing, the Transformer Circuits posts by Anthropic are great. In particular, it was only after reading one of these that I started thinking of the combination of the value and output matrices as being a combined low-rank map from…