JAX in 100 Seconds

JAX is a Python library similar to NumPy for scientific computing and linear algebra, but designed to run on accelerators like Cuda-based GPUs and Google's TPUs.

#programming #math #100SecondsOfCode

💬 Chat with Me on Discord

🔗 Resources

🔥 Get More Content - Upgrade to PRO

Use code YT25 for 25% off PRO access

🎨 My Editor Settings

- Atom One Dark
- vscode-icons
- Fira Code Font

🔖 Topics Covered

- JAX basics tutorial
- How does JAX work?
- JAXPpython explained quickly
- Pytorch alternative
- Tensorflow vs JAX
- How is calculus used on Machine Learning

[dtoaster]

"Why did you start using JAX?"
Me: "I like the logo"

[justingolden]

"Imagine you're writing a nuclear warhead in your mom's basement" Oh I don't have to imagine fireship

[rafaelsanchezmartinez]

Now I have 10 years of experience in JAX. NICE!

[jonathansmith]

Active: Jax enters Evasion, a defensive stance, for up to 2 seconds, causing all basic attacks against him to miss. Jax also takes 25% reduced damage from all champion area of effect abilities. After 1 second, Jax can reactivate to end it immediately.

[wlockuz]

As a software engineer with 10 years of experience, I understood some of those words.

[mritunjaymusale]

Jax sounds like less abstract version of pytorch and more complicated version of numpy

[alcoholrelated]

i'm interested in computer science, calculus and statistics, but i only have 300 seconds in total

[potato_zeq]

"Imagine if i had a real weapon!"

[unclecode]

The sample code u shared at the end, so simple & elegant shows what training is all about. Approximation of a function F defined as multiplication of multiple matrixes (its layers), then calculating its error over known data E(F(x), y), computing gradients of that error E', & then updating F's parameters, such E' approach to zero. I will share this code to my students. Thanks again.

[VisibilityO]

I have never heard the best explanation of derivative from calculus like 'if you want to know how big is the mushroom cloud is growing ' .

[netcodedev]

I just opened YouTube and thought it must be about time for a new fireship video. And bang! There it is

[hectors.]

A must like video, due to your effort to research this type of content, keep that good work

[Henrique-upsu]

"Let's start with X: Accelerated (...)"

"???"

[bramvdnheuvel]

Do Elm in 100 seconds! You'll love it! It's an older JavaScript framework that had a lot of thought behind it. It's funny to see more popular ones catch up, but Elm did a lot of the things very well and it deserves some love!

[athlone_tch]

- “Mum, could I practice my predictions from automatic differentiation in our garden?”
1:47

[zstrizzel]

great video but still very sad we did not work in a mortal kombat jax reference

[robertholtz]

Thank you, Fireship. Up until I watched this video, I thought I was smart.

[MarcusAurelius-klyz]

Dang missed opportunity using the Jax from league of legends on the video

[codexcursors]

Thanks, I can now add 10 years experience of JAX to my résumé!

[utorque]

Could you do a ROCm video (AMD's CUDA couterpart) ? Love you and your vids !