Neural Tangents
A high-level neural network API for specifying and analyzing infinite-width neural networks as Gaussian Processes in Python.
What is Neural Tangents?
Neural Tangents is a Python library for working with infinite-width neural networks, treating them as Gaussian Processes with computable kernels. It allows researchers to analyze neural network architectures in their infinite limit, providing tools to compute the Neural Tangent Kernel (NTK) and Neural Network Gaussian Process (NNGP) kernel directly from network specifications.
Machine learning researchers and practitioners studying neural network theory, kernel methods, or training dynamics, particularly those interested in the infinite-width limit of deep learning models.
It uniquely combines ease of use with theoretical rigor, offering a high-level API compatible with JAX to compute infinite network kernels analytically, enabling fast experimentation without sacrificing performance or scalability.
Overview
Fast and Easy Infinite Neural Networks in Python
Use Cases
Best For
- Studying the infinite-width limit of neural network architectures
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
