JAX
JAX is a Python library for high-performance array computing, with composable transformations for automatic differentiation, compilation, vectorization, and parallelization.
Deep Learning with JAX
A functional-first numerical computing library for machine learning and scientific computing in which state is made explicit and transformations like autodiff and compilation are central.
- How it is used
- Deploys NumPy-style numerical programs for differentiable, compiled, vectorized, and parallel machine-learning or scientific computation.
- How deep it goes
- Explains arrays, functional state, four core transformations, hardware, and ecosystem tradeoffs, while deferring detailed chapters on each feature.
- Examples
- Uses immutable indexed updates, performance comparisons, and an MNIST neural network combining gradients, compilation, and auto-vectorization.
- What you can do after
- Build a simple MNIST neural network using explicit state and grad(), jit(), and vmap().
Deep Learning with R, Third Edition
JAX is a Python library for high-performance numerical computing and machine learning with composable transformations such as automatic differentiation and just-in-time compilation.
- How it is used
- Provides low-level numerical computation and automatic differentiation, both directly and as a Keras backend.
- How deep it goes
- Works through stateless gradients, compilation, custom training, and distributed configuration, while leaving cloud VM provisioning to external instructions.
- Examples
- Uses a linear classifier, an MNIST custom training step, and top-class gradients for convolutional network interpretation.
- What you can do after
- Builds a linear classifier from scratch and configures Keras data parallelism with JAX.
Deep Learning with Python, Third Edition
A numerical computing and machine learning library for high-performance array computation, automatic differentiation, and compilation.
- How it is used
- Supports low-level differentiable computation and serves as a Keras backend for neural-network training.
- How deep it goes
- Develops stateless training steps with explicit state, automatic differentiation, and compilation, including a custom Keras optimizer update.
- Examples
- Works through a linear classifier, a custom Keras training step, and gradient ascent on an image.
- What you can do after
- Apply it via JAX to write a stateless linear-classifier training loop and compute gradients.
Read how Deep Learning with Python, Third Edition explains JAX →
Also covered in
What to know first
- arrayAn array is an ordered collection of elements organized in one or more dimensions and accessible by position or index.
- automatic differentiationAutomatic differentiation is a computational technique that evaluates derivatives of a program by systematically applying the chain rule to its elementary operations.
- code compilationCode compilation is the transformation of source code or another formal representation into executable code or an intermediate or lower-level representation for execution or further processing.
- computation graphA computation graph is a directed graph whose nodes represent computational operations or values and whose edges represent dependencies between them.
Related concepts
- functional programminguses · Functional programming is a programming paradigm that expresses computation through the evaluation and composition of functions, typically favoring immutable data and minimizing mutable state and side effects.
- automatic differentiationuses · Automatic differentiation is a computational technique that evaluates derivatives of a program by systematically applying the chain rule to its elementary operations.
- jax.numpyimplements · jax.numpy is JAX’s NumPy-compatible API for creating and manipulating arrays while supporting JAX transformations.
- PyTorchcontrasts with · PyTorch is an open-source machine-learning framework that provides tensor computation, automatic differentiation, and tools for developing and training neural networks.
- TPUuses · A Tensor Processing Unit (TPU) is a specialized processor developed by Google to accelerate machine-learning computations, particularly tensor operations.
- XLAuses · XLA (Accelerated Linear Algebra) is a compiler that optimizes and compiles machine-learning and array computations for supported hardware.
Questions about JAX
What is JAX?
JAX is a Python library for high-performance array computing, with composable transformations for automatic differentiation, compilation, vectorization, and parallelization.
Which Manning books explain JAX?
Deep Learning with JAX, Deep Learning with R, Third Edition and Deep Learning with Python, Third Edition.
What should I know before learning JAX?
Manning books that teach JAX usually introduce array, automatic differentiation, code compilation and computation graph first.
What is the difference between JAX and PyTorch?
JAX is a Python library for high-performance array computing, with composable transformations for automatic differentiation, compilation, vectorization, and parallelization. PyTorch is an open-source machine-learning framework that provides tensor computation, automatic differentiation, and tools for developing and training neural networks.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.


