Discover the power of JAX in deep learning. Gain insights into its ecosystem and learn about linear algebra, pseudo-random number generation, and optimization algorithms for cleaner, structured coding.

Doxx.tar.gz

NormalCode

JuPyter

JAX is a Python library designed for high-performance ML research. It is a powerful numerical computing library, just like Numpy, but with some key improvements.

In this course, you will learn all about JAX and its ecosystem of libraries (Haiku, Jraph, Chex, Flax, Optax). Addressing a wide range of audiences, you will cover several topics including linear algebra, random variables theory, pseudo-random number generation, and optimization algorithms.

By the end of this course, you will have a new set of skills that will make deep learning programming more intuitive, structured, and clean.

Introduction to JAX and Deep Learning

Which of the followings sequence models uses filters?

Which of the followings sequence models uses filters?

Applying a non-overlapping max-pooling of $3\times3$ on a $32\times32$ image will result in a size of:

Applying a non-overlapping max-pooling of <math><semantics><mrow><mn>3</mn><mo>×</mo><mn>3</mn></mrow><annotation encoding="application/x-tex">3\times3</annotation></semantics></math>3×3 on a <math><semantics><mrow><mn>3</mn><mn>2</mn><mo>×</mo><mn>3</mn><mn>2</mn></mrow><annotation encoding="application/x-tex">32\times32</annotation></semantics></math>32×32 image will result in a size of:

$25%$ of neurons will not learn in every epoch.

$25%$ of neurons will be picked randomly in each epoch and not learn in the given epoch.

$75%$ of neurons will not learn in every epoch.

$75%$ of neurons will be picked randomly in each epoch and not learn in the given epoch.

What does **`y = nn.Dropout(rate=0.25) `** mean?

What does <code>y = nn.Dropout(rate=0.25) </code> mean?

When gradients become too large and result in a term approaching $\infty$

When gradients become too small and approach $0$.

What is the "exploding gradients" phenomenon?

What is the “exploding gradients” phenomenon?

Introduction

JAX Programming Model

Linear Algebra

Random Variables and Distributions

JAX Ecosystem

Project: GAN Using the JAX ecosystem

Appendix

Quiz: Flax