CMU Advanced NLP Fall 2024 (4): Attention and Transformers

Why it's on BrighterTube

Advanced · Editorial review · 85% confidence

Full-course playlist 'CMU Advanced NLP Fall 2024' from a curated course list (CMU Advanced NLP Fall 2024 (Lectures - Fall 2024) (Lectures - Fall 2021)); uploader is instructor; playlist judged: Full-length graduate NLP lecture series uploaded by the instructor himself, covering substantive technical topics in depth.; title passed a strict title check; oEmbed verified.

What you'll learn

A 79-minute video from Graham Neubig: “CMU Advanced NLP Fall 2024 (4): Attention and Transformers”.

Programming & CS

Video by Graham Neubig, played through YouTube's embedded player.

38:24

CMU Neural Nets for NLP 2021 (7): Attention Graham NeubigProgramming & CS

58:24

CMU Neural Nets for NLP 2021 (2): Language Modeling, Efficiency/Training Tricks Graham NeubigProgramming & CS

But what is a neural network? | Deep learning chapter 1 3Blue1BrownScience & Math

Intro25.1M views

Let's build GPT: from scratch, in code, spelled out.Andrej KarpathyProgramming & CS

8.21M views

Transformers, the tech behind LLMs | Deep Learning Chapter 5 3Blue1BrownProgramming & CS

Intro11.6M views

The spelled-out intro to neural networks and backpropagation: building micrograd Andrej KarpathyProgramming & CS

Intro4.41M views

24:26

The Beauty of Bézier Curves Freya HolmérProgramming & CS

2.23M views

2:27:41

CS50x 2024 - Lecture 1 - C CS50Programming & CS

Intro1.41M views

“Hello, world” from scratch on a 6502 — Part 1 Ben EaterProgramming & CS

5.85M views

Ruby Conf 12 - Y Not- Adventures in Functional Programming by Jim Weirich ConfreaksProgramming & CS

65.7K views

2:04:55

CS50x 2024 - Lecture 0 - Scratch CS50Programming & CS

Intro2.2M views

RailsConf 2014 - All the Little Things by Sandi Metz ConfreaksProgramming & CS

190K views

38:24

CMU Neural Nets for NLP 2021 (7): Attention

Graham Neubig

A 38-minute video from Graham Neubig: “CMU Neural Nets for NLP 2021 (7): Attention”.

58:24

CMU Neural Nets for NLP 2021 (2): Language Modeling, Efficiency/Training Tricks

Graham Neubig

A 58-minute video from Graham Neubig: “CMU Neural Nets for NLP 2021 (2): Language Modeling, Efficiency/Training Tricks”.

But what is a neural network? | Deep learning chapter 1

3Blue1Brown

Intro25.1M views

Builds up what a neural network actually is — neurons as numbers, layers, weights and biases — using handwritten-digit recognition as the running example.

Let's build GPT: from scratch, in code, spelled out.

Andrej Karpathy

8.21M views

Building a GPT-style language model from scratch in code, following 'Attention Is All You Need'.

Transformers, the tech behind LLMs | Deep Learning Chapter 5

3Blue1Brown

Intro11.6M views

How transformer models (the 'T' in GPT) turn text into vectors and predict the next token, step by step.

The spelled-out intro to neural networks and backpropagation: building micrograd

Andrej Karpathy

Intro4.41M views

Building micrograd, a tiny autograd engine, to understand backpropagation completely.

24:26

The Beauty of Bézier Curves

Freya Holmér

2.23M views

Freya Holmér builds Bézier curves from linear interpolation up, covering de Casteljau's algorithm, derivatives, arc length and their use in games and graphics.

2:27:41

CS50x 2024 - Lecture 1 - C

CS50

Intro1.41M views

CS50x 2024 lecture 1: an introduction to C — syntax, types, conditionals, loops and compiling.

“Hello, world” from scratch on a 6502 — Part 1

Ben Eater

5.85M views

Building a computer around the 6502 processor on a breadboard and running 'Hello, world'.

Ruby Conf 12 - Y Not- Adventures in Functional Programming by Jim Weirich

Confreaks

65.7K views

Jim Weirich derives the Y combinator live, step by step, using nothing but Ruby lambdas, and along the way teaches the refactorings of lambda calculus.

2:04:55

CS50x 2024 - Lecture 0 - Scratch

CS50

Intro2.2M views

CS50x 2024 lecture 0: how computers represent information, algorithms, and first programs in Scratch.

RailsConf 2014 - All the Little Things by Sandi Metz

Confreaks

190K views

Sandi Metz refactors the notorious Gilded Rose kata live, showing how small, disciplined steps and duplication-over-wrong-abstraction lead to clean object-oriented code.