Foundational Math for Generative AI: Understanding LLMs and Transformers through Practical Applications

Course details

Unlock the mysteries behind the models powering today’s most advanced AI applications. In this course, instructor Axel Sirota takes you beyond just using large language models (LLMs) like BERT or GPT and highlights the mathematical foundations of generative AI. Explore the challenge of sentiment analysis with simple recurrent neural networks (RNNs) and progressively evolve your approach as you gain a deep understanding of attention mechanisms, transformers, and models. Through intuitive explanations and hands-on coding exercises, Axel outlines why attention revolutionized natural language processing, and how transformers reshaped the field by eliminating the need for RNNs altogether. Along the way, get tips on fine-tuning pretrained models, applying cutting-edge techniques like low-rank adaptation (LoRA), and leveraging your newly acquired skills to build smarter, more efficient models and innovate in the fast-evolving world of AI.

Learning objectives
Gain an intuitive understanding of how and why LLMs and transformers work.
Learn how attention mechanisms evolved to solve key problems in RNN-based models.
Develop a sentiment analysis model using TensorFlow, Keras, and Hugging Face’s DistilBERT.
Enhance models progressively with mathematical insights applied in code, from word embeddings to attention and transformer layers.
Use visualizations to grasp how attention and optimization work.

Concepts

0. Introduction

01 - Intro to foundational math for generative AI
02 - Getting the most out of this course
03 - Version check

1. Introduction to Math for GenAI and Attention Basics

04 - Why LLMs and attention matter
05 - RNNs and the context bottleneck problem
06 - Demo - Building a simple RNN model for sentiment analysis
07 - Introduction to attention - Bahdanau s solution
08 - Demo - Adding attention to an RNN model
09 - Solution - Implement Bahdanau's attention

2. Transformers - Removing RNNs for More Efficient Models

10 - From RNNs to transformers
11 - Understanding self-attention in transformers
12 - Multi-head attention and positional encoding
13 - Building a transformer model for sentiment analysis
14 - Solution - Build a two-layer transformer encoder

3. Deep Dive into LLMs and Model Fine-Tuning

15 - The three types of LLMs
16 - Special decoder-only models
17 - Explaining encoder-only models like BERT
18 - Fine-tuning DistilBERT for sentiment analysis
19 - Attention masks in transformers
20 - Solution - Detect irony and climate stance in TweetEval

Conclusion

21 - Course summary and next steps

Foundational Math for Generative AI: Understanding LLMs and Transformers through Practical Applications

Authors

Axel Sirota