Learning JAX

سرفصل های دوره

In this course, instructor Janani Ravi gives you an in-depth look at JAX, a new experimental Python library designed for high performance, scientific computing and machine learning. Janani takes you through all aspects of JAX and what it is capable of, including: just-in-time compilation; automatic vectorization and automatic parallelization; computing gradients; performing transformations on pytrees; training simple neural networks; and more.

01 - Introduction

01 - Prerequisites

02 - What is JAX

03 - Why use JAX

04 - Choosing JAX

05 - JAX vs. TensorFlow vs. PyTorch

06 - Getting set up with Colab

02 - 1. Working with JAX Arrays

01 - JAX arrays

02 - JAX arrays and NumPy arrays Similarities

03 - JAX arrays and NumPy arrays Differences

04 - Asynchronous dispatch and JAX array speed up

03 - 2. Just-in-Time Compilation

01 - Composable function transformations

02 - JIT and pure functions

03 - Using JIT

04 - Tracer objects in JIT

05 - Impure functions and JIT IO streams

06 - Impure functions and JIT Global state

07 - Impure functions and JIT Iterators

08 - Jaxprs

09 - Control flow statements and JIT

10 - Static arguments in jitted functions

11 - Lambdas and JIT

04 - 3. Automatic Vectorization and Automatic Parallelization

01 - Understanding vectorization and parallelization

02 - Automatic vectorization

03 - Comparing naive and manual batching with automatic vectorization

05 - 4. Computing Gradients

01 - Understanding gradient computation

02 - Gradient computation

03 - Higher order gradients

04 - Jacobians and Hessians

06 - 5. Performing Transformations on pytrees

01 - Understanding pytrees

02 - Simple pytrees

03 - Operations on pytrees

04 - Pytree containers

05 - Custom containers as pytrees

07 - 6. Training Simple Neural Networks

01 - Regression using a single neuron Loading and preprocessing data

02 - Regression using a single neuron Helper functions

03 - Regression using a single neuron Training and evaluating a model

04 - Regression using a neural network Helper functions

05 - Regression using a neural network Training a model and visualizing results

06 - Classification using neural network Loading and preprocessing data

07 - Classification using neural network Training and evaluating model

08 - Conclusion

01 - Summary and next steps

189,000 تومان

افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: LinkedIn Learning (Lynda)