Completed
- 02:40:48 Transformers Lesson: Rotary Positional Embeddings RoPE
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Become an AI Researcher - LLM, Math, PyTorch, Neural Networks, Transformers
Automatically move to the next video in the Classroom when playback concludes
- 1 - 00:00:00 Welcome & Course Overview
- 2 - 00:05:28 Requirements & Setup for the Course
- 3 - 00:10:48 Math Lesson: Functions Linear, Quadratic, Cubic, Square Root
- 4 - 00:19:10 Math Lesson: Derivatives Rate of Change
- 5 - 00:33:19 Math Lesson: Vectors Magnitude, Dot Product, Normalization
- 6 - 00:46:07 Math Lesson: Gradients Steepest Ascent/Descent, Partial Derivatives
- 7 - 00:55:03 Math Lesson: Matrices Multiplication, Transpose, Identity
- 8 - 01:08:39 Math Lesson: Probability Expected Value, Conditional Probability
- 9 - 01:19:19 START: PyTorch Fundamentals & Creating Tensors
- 10 - 01:26:03 PyTorch Lesson: Reshaping and Viewing Tensors
- 11 - 01:27:48 PyTorch Lesson: Squeezing and Unsqueezing Dimensions
- 12 - 01:41:02 PyTorch Lesson: Indexing and Slicing Tensors
- 13 - 01:49:55 PyTorch Lesson: Special Tensors Zero, Ones, Linspace
- 14 - 01:54:00 START: Coding Neural Networks from Scratch
- 15 - 01:54:29 Neural Networks Lesson: Single Neuron Weights, Bias, Weighted Sum
- 16 - 01:57:11 Neural Networks Lesson: Activation Functions Sigmoid, ReLU, tanh
- 17 - 02:03:07 Neural Networks Lesson: Multi-Layer Networks & Backpropagation
- 18 - 02:11:59 START: Understanding Transformers for LLMs
- 19 - 02:14:14 Transformers Lesson: Attention Mechanism Query, Key, Value
- 20 - 02:32:39 Transformers Lesson: Self-Attention & Causal Self-Attention
- 21 - 02:40:48 Transformers Lesson: Rotary Positional Embeddings RoPE
- 22 - 02:44:07 Transformers Lesson: Multi-Head Attention
- 23 - 02:55:03 Transformers Lesson: Transformer Block Feed-Forward, Add & Norm
- 24 - 03:04:15 Tokenization for GPT Architecture
- 25 - 03:06:47 Conclusion & Next Steps
