1 option
Deep Learning with JAX.
- Format:
- Book
- Author/Creator:
- Sapunov, Grigory.
- Language:
- English
- Subjects (All):
- Deep learning (Machine learning).
- Functional programming (Computer science).
- Physical Description:
- 1 online resource (344 pages)
- Edition:
- 1st ed.
- Place of Publication:
- New York : Manning Publications Co. LLC, 2024.
- Summary:
- This book explores JAX, a cutting-edge Python library for deep learning and numerical computation developed by Google. It emphasizes functional programming and introduces powerful capabilities such as gradient computation, Just-In-Time (JIT) compilation, and support for GPUs and TPUs. Aimed at individuals with a foundational understanding of deep learning and Python, the book provides comprehensive guidance on JAX concepts, including its ecosystem and applications. It covers topics such as image processing, neural network training, parallel computing, tensor sharding, and working with complex data structures. The author seeks to consolidate scattered resources and make JAX accessible to researchers and professionals in fields like machine learning, physics, and large-scale simulations. By offering practical examples and insights, the book enables readers to integrate JAX into their projects and stay updated with its evolving capabilities. Generated by AI.
- Contents:
- Deep Learning with JAX
- Copyright
- dedication
- contents
- front matter
- preface
- acknowledgments
- about this book
- Who should read this book?
- How this book is organized: A roadmap
- About the code
- liveBook discussion forum
- Other online resources
- about the author
- about the cover illustration
- Part 1. First steps
- 1 When and why to use JAX
- 1.1 Reasons to use JAX
- 1.1.1 Computational performance
- 1.1.2 Functional approach
- 1.1.3 JAX ecosystem
- 1.2 How is JAX different from NumPy?
- 1.2.1 JAX as NumPy
- 1.2.2 Composable transformations
- 1.3 How is JAX different from TensorFlow and PyTorch?
- Summary
- 2 Your first program in JAX
- 2.1 A toy ML problem: Classifying handwritten digits
- 2.2 An overview of a JAX deep learning project
- 2.3 Loading and preparing the dataset Generated by AI.
- Notes:
- Description based on publisher supplied metadata and other sources.
- Part of the metadata in this record was created by AI, based on the text of the resource.
- ISBN:
- 9781638355755
- 1638355754
- 9781633438880
- 1633438880
- OCLC:
- 1468666460
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.