# google/neural-tangents

Fast and Easy Infinite Neural Networks in Python

Repository: https://github.com/google/neural-tangents
Canonical: https://ross.abutalabs.com/products/neural-tangents
Homepage: https://iclr.cc/virtual_2020/poster_SklD9yrFPS.html
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: neural-networks, infinite-networks, gaussian-processes, training-dynamics, neural-tangents, jax, kernel, deep-networks, kernel-computation, gradient-descent, bayesian-networks, bayesian-inference, gradient-flow
Archived: true
Last push: 2024-03-01T17:17:03+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2704, "days_push": 915, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2383, forks 238 (observed 2026-08-28T04:06:42.446179+00:00)

## What it is
Neural Tangents is a Python library built on JAX for defining, training, and evaluating neural networks of both finite and infinite width. It computes the exact Gaussian Process kernels (NTK and NNGP) of complex architectures and enables analytic Bayesian inference or gradient-descent training in the infinite-width limit.

## Use cases
- compute the neural tangent kernel of a CNN or transformer
- train an infinite-width network as a Gaussian process
- study gradient descent training dynamics of wide networks
- run exact Bayesian inference with NNGP kernels
- compare finite and infinite network behavior in research
- scale kernel computations across GPUs or TPUs

## When to choose
- you need exact NTK/NNGP kernel computations for research
- you want to study infinite-width limits of neural networks
- you work in JAX and need composable layer primitives with kernel tracking
- you need multi-device distributed kernel computation

## When to avoid
- you need a general-purpose deep learning framework for production models
- you require PyTorch or TensorFlow ecosystems
- your use case is standard finite-width training without kernel analysis

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, math, sdk
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python, cross-platform, cli
- tags: jax, neural-tangent-kernel, gaussian-processes, infinite-width-networks, bayesian-inference, kernel-methods, research, gpu

## Member repositories
- google/neural-tangents (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:42.446179+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:34:41.652855+00:00, confidence not recorded.
  - readme: https://github.com/google/neural-tangents (fetched 2026-08-28T04:06:42.446179+00:00, sha a92987b8a22d)
  - homepage: https://iclr.cc/virtual_2020/poster_SklD9yrFPS.html (fetched 2026-08-29T10:15:37.981072+00:00, sha 8c75437e15a7)
  - site_page: https://iclr.cc/virtual_2020/about.html (fetched 2026-08-29T10:15:37.984746+00:00, sha e1e10e9217e3)
  - registry_pypi: https://pypi.org/pypi/neural-tangents/json (fetched 2026-08-29T10:15:37.986876+00:00, sha a7deac3307a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.