Vizuara Books
Transformers: Theory, intuition, and Building from Scratch
Free preview available. Sign in and subscribe to unlock the full book.
Vizuara AI Labs · intermediate

Transformers: Theory, intuition, and Building from Scratch

The transformer, from intuition to code.

Attention, positional encoding, and the full transformer architecture built from first principles and illustrated.

intermediatetransformersattentionfrom-scratchnlp
20 capsules92 figures~5 hoursby Dr. Raj Dandekar

Read on your Kindle

We'll send this whole book straight to your Kindle — it opens natively, so you can resize the text, read fully offline, and it remembers where you left off. Nothing to download or manage.

Sending to Kindle is for subscribers — subscribe to read the whole library on your Kindle.

00Introduction and Motivation2 capsules

Introduction and Motivation — 2 chapters.

01Example/Motivationfree13 min02Course Introductionconcept🔒12 min
01Foundations of Attention2 capsules

Foundations of Attention — 2 chapters.

03Understanding Attention🔒14 min04Attention Example🔒14 min
02Challenges with Traditional Models1 capsules

Challenges with Traditional Models — 1 chapters.

05Shortcomings of Sequence-to-Sequence Models🔒14 min
03Introduction to Transformers2 capsules

Introduction to Transformers — 2 chapters.

06Word Embeddings🔒13 min07Transformer Model Introconcept🔒14 min
04Positional Encoding4 capsules

Positional Encoding — 4 chapters.

08Why Do We Need Positional Encoding?🔒14 min09Approaching Positional Encoding🔒14 min10Sinusoidal Encoding🔒13 min11Other Positional Encodings🔒14 min
05Attention Mechanisms in Transformers3 capsules

Attention Mechanisms in Transformers — 3 chapters.

12Intro to Attention in Transformersconcept🔒14 min13Scaled Dot-Product Attentionmath🔒14 min14Multi-Head Attention🔒14 min
06Piecing It All Together2 capsules

Piecing It All Together.

15The Encoder Blockconcept🔒13 min16The Decoder and Final Outputconcept🔒13 min
07Implementation & Code Walkthrough3 capsules

Implementation & Code Walkthrough.

17Tokenization and the Datasetcode🔒14 min18Coding the Input and Attention Layerscode🔒13 min19Assembling and Training the Transformercode🔒14 min
08Extensions and Advanced Topics1 capsules

Extensions and Advanced Topics.

20Other Transformer-Based Architecturesconcept🔒12 min

Ratings & reviews

No ratings yet. Yours would be the first.

Sign in to rate this book