Neural Tangents Files

Fast and Easy Infinite Neural Networks in Python

This is an exact mirror of the Neural Tangents project, hosted at https://github.com/google/neural-tangents. SourceForge is not affiliated with Neural Tangents. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
neural-tangents-0.6.0.tar.gz	2022-07-18	227.3 kB	0
neural_tangents-0.6.0-py2.py3-none-any.whl	2022-07-18	241.9 kB	0
README.md	2022-07-18	2.4 kB	0
v0.6.0 source code.tar.gz	2022-07-18	4.4 MB	0
v0.6.0 source code.zip	2022-07-18	4.4 MB	0
Totals: 5 Items		9.3 MB	0

New features: * nt.empirical: * New implementation=3 for nt.empirical, allowing to often speed-up or reduce the memory of the empirical NTK by orders of magnitude. Please see our ICML2022 paper Fast Finite Width Neural Tangent Kernel, new empirical NTK examples, and visit us on Thursday at ICML in-person! * New experimental prototype of using our empirical NTK implementations in Tensorflow via nt.experimental.empirical_ntk_fn_tf. * Make nt.empircial work with arbitrary pytrees.

nt.stax:
- nt.stax.Index layer mimicking numpy indexing.
- Expose the layer scaling parameter s in parameterization="standard".

Improvements: * Slightly lower memory usage in batching. * Many improvements to documentation and type annotations. * Simplify test specifications and avoid relying on JAX testing utilities.

Bugfixes: * Make nt.batch use the correct (local) number of devices in a multi-host setting (thanks @jglaser).

Breaking changes: * If you've been using nt.empirical or nt.monte_carlo with mask_constant (empirical kernels with masking, for variable-lengths sequences), you now need to pass nt.empirical_kernel_fn(stax.unmask_fn(apply_fn)) instead of nt.empirical_kernel_fn(apply_fn). This is done in order to decouple nt.empirical and nt.stax, and the under-the-hood unmasking happening in nt.empirical is now delegated to stax.unmask_fn.

Source: README.md, updated 2022-07-18

Other Useful Business Software

Gen AI apps are built with MongoDB Atlas Icon

Gen AI apps are built with MongoDB Atlas

The database for AI-powered applications.

MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.

Start Free

Build Securely on Azure with Proven Frameworks Icon

Build Securely on Azure with Proven Frameworks

Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.

Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.

Download Now

Recommended Projects

NeuralSyns
NeuralSyns is a neural simulator for large spiking networks. New neuron and synapse dynamics can be added, and complex network models can be easily built using the included tool NetBuilder. OpenGL is used to show the network's architecture and activity.
Intel neon
neon is Intel's reference deep learning framework committed to best performance on all hardware. Designed for ease of use and extensibility. See the new features in our latest release. We want to highlight that neon v2.0.0+ has been optimized for much better performance on CPUs by enabling Intel...
NeuroNet
Neural network program. Creates and trains neural networks, shows data.
IEEE 802.1d ethernet bridging
IEEE 802.1d ethernet bridging (plus Spanning Tree protocol) for the linux kernel. Kernel code is in Linux 2.4 and 2.6 kernels.
Make-A-Video - Pytorch (wip)
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch. They combine pseudo-3d convolutions (axial convolutions) and temporal attention and show much better temporal fusion. The pseudo-3d convolutions isn't a new concept. It has been explored before in other...