Deep Dive into the Transformer Encoder Architecture

Deep Dive into the Transformer Encoder Architecture

CodeEmporium via YouTube Direct link

Introduction

1 of 16

1 of 16

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Deep Dive into the Transformer Encoder Architecture

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Encoder Overview
  3. 3 Blowing up the encoder
  4. 4 Create Initial Embeddings
  5. 5 Positional Encodings
  6. 6 The Encoder Layer Begins
  7. 7 Query, Key, Value Vectors
  8. 8 Constructing Self Attention Matrix
  9. 9 Why scaling and Softmax?
  10. 10 Combining Attention heads
  11. 11 Residual Connections Skip Connections
  12. 12 Layer Normalization
  13. 13 Why Linear Layers, ReLU, Dropout
  14. 14 Complete the Encoder Layer
  15. 15 Final Word Embeddings
  16. 16 Sneak Peak of Code

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.