Introducing Nx - José Valim | Lambda Days 2021
Channel:Code Sync · Length:52:58 · Published:2021-02-19 · Views:26274
Summary
Jose Valim introduces Nx, the project bringing numerical computing to Elixir, covering multi-dimensional tensors, automatic differentiation and JIT compilation to CPU and GPU.
Why HN recommends it
Recommended in Elixir and machine learning threads as the introduction to what Nx makes possible.
I recommend you watching José’s talk introducing Elixir Nx — HN, 2021
Functional programming · Machine learning & deep learning
Subtitles (excerpt)
[Music] hi i am jose vallin creator of elixir and today i would like to talk to you about a new project called nx that stands for numerical elixir and our goals for this project and how we are going to use this project and a couple of related projects to enable elixir for numerical computing okay so let's get started nx at the moment right is is this idea of numerical elixir but it's also a library that comes with a couple of things that we're exploring the talk nx is about multi-dimensional type the race aka tensors okay it's about numerical definitions it's about automatic differentiation and it's about just in time and aot stage compilation to the cpu and the gpu and this is exactly what we are going to explore in this talk those are the topics for this talk and in order to show how those things work what we will do is that we will live code a neural network from scratch now is a good time to make one disclaimer which is uh although i'm going to live code the neural network sometimes i'm going to gloss over the neural network details i'm going to say something like hey uh we're going to use this formula and this is the name of the formula and we know that this formula is good but to fully understand
On Hacker News
If you have not been following the work José and Sean have been doing lately, I recommend you watching José’s talk introducing Elixir Nx [VIDEO] — bfm, 2021-04
Lots of people mention Nx and of course I want to do the same but with a link to a youtube video, in case you wonder what's possible currently. [VIDEO] — rmetzler, 2021-03
Although it's early days, José Valim and some other folks are working on adding AI-related capabilities to Elixir and the (Erlang) BEAM. See "Introducing Nx" ( [VIDEO] ) for an intro. Given that they already have a robust Actor model as a base to work from, it occurs to me that they may be able to use some of Ray's ideas as they go along... — Rich_Morin, 2021-07
Related videos
- Ruby Conf 12 - Y Not- Adventures in Functional Programming by Jim Weirich · Confreaks · 53:21
- The spelled-out intro to neural networks and backpropagation: building micrograd · Andrej Karpathy · 2:25:52
- The Soul of Erlang and Elixir • Sasa Juric • GOTO 2019 · GOTO Conferences · 42:02
- "Simple Made Easy" - Rich Hickey (2011) · Strange Loop Conference · 1:01:38
- But what is a neural network? | Deep learning chapter 1 · 3Blue1Brown · 18:40
- "Making Impossible States Impossible" by Richard Feldman · elm-conf · 25:06
- William Byrd on "The Most Beautiful Program Ever Written" [PWL NYC] · PapersWeLove · 1:31:05
- The Value of Values with Rich Hickey · InfoQ · 31:43
- Why Isn't Functional Programming the Norm? – Richard Feldman · Metosin · 46:09
- AlphaGo - The Movie | Full award-winning documentary · Google DeepMind · 1:30:28
- Maybe Not - Rich Hickey · ClojureTV · 1:03:28
- Solving Problems the Clojure Way - Rafal Dittwald · Clojure/north · 1:02:26
- Transformers, the tech behind LLMs | Deep Learning Chapter 5 · 3Blue1Brown · 27:14
- Lecture 1A: Overview and Introduction to Lisp · MIT OpenCourseWare · 1:12:55
- Conway's Game Of Life in APL · Dyalog · 7:47
- Lecture 1A | MIT 6.001 Structure and Interpretation, 1986 · MIT OpenCourseWare · 1:12:55