arXiv Analytics

Sign in

arXiv:1912.02803 [stat.ML]AbstractReferencesReviewsResources

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

Roman Novak, Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander A. Alemi, Jascha Sohl-Dickstein, Samuel S. Schoenholz

Published 2019-12-05Version 1

Neural Tangents is a library designed to enable research into infinite-width neural networks. It provides a high-level API for specifying complex and hierarchical neural network architectures. These networks can then be trained and evaluated either at finite-width as usual or in their infinite-width limit. Infinite-width networks can be trained analytically using exact Bayesian inference or using gradient descent via the Neural Tangent Kernel. Additionally, Neural Tangents provides tools to study gradient descent training dynamics of wide but finite networks in either function space or weight space. The entire library runs out-of-the-box on CPU, GPU, or TPU. All computations can be automatically distributed over multiple accelerators with near-linear scaling in the number of devices. Neural Tangents is available at www.github.com/google/neural-tangents. We also provide an accompanying interactive Colab notebook.

Related articles: Most relevant | Search more
arXiv:1910.08013 [stat.ML] (Published 2019-10-17)
Why bigger is not always better: on finite and infinite neural networks
arXiv:2107.12723 [stat.ML] (Published 2021-07-27)
Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel
arXiv:2005.11879 [stat.ML] (Published 2020-05-25)
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks