Course Curriculum

    1. Context

    2. Why This Matters?

    3. Learning Objectives

    1. Strengths and Weaknesses in LLMs

    2. Discriminative vs Generative AI

    3. Generative vs Discriminative AI

    1. Transformers

    2. Embeddings

    3. Attention

    4. Introduction to Transformers

    1. Similarity

    2. Three Ways to Measure Similarity

    3. Keys and Queries Matrices

    4. Linear Transformations: How Weights Change Similarity

    5. Multi-Head Attention

    6. Attention Mechanism

    7. Sentiment Analysis

    8. Applications

    9. Attention Mechanism

    1. Feedforward Neural Networks

    2. Types of Neural Networks

    3. Softmax

    4. How Do We Build Embeddings?

    5. Tokenization

    6. Positional Encoding

    7. Transformer Architecture

    8. Revisiting LLMs

    9. Neural Networks and LLM Fundamentals

    1. Introduction

    2. Learning Objectives

    3. How Does Tokenization Work?

    4. Tokenizing a Song

    5. Impact of Language Complexity

    6. Punctuation Sensitivity

About this course

  • Free
  • 42 lessons
  • 2.5 hours of video content