Metadata-Version: 2.4
Name: eventax
Version: 0.1.0
Summary: A Diffrax-based framework for continuous-time spiking neural networks 
Home-page: https://github.com/Efficient-Scalable-Machine-Learning/eventax
Author: Lukas König
Author-email: lukmkoenig@gmail.com
License: MIT
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: jax>=0.9.1
Requires-Dist: diffrax>=0.7.2
Requires-Dist: equinox>=0.13.5
Dynamic: author
Dynamic: author-email
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

<p align="center">
  <img src="./docs-site/docs/img/logo5.svg" alt="Eventpropjax" width="70%">
</p>

Eventax provides a [JAX](https://github.com/google/jax) implementation of the [EventProp algorithm](https://arxiv.org/abs/2009.08378) using [Diffrax](https://github.com/patrick-kidger/diffrax) and [Equinox](https://github.com/patrick-kidger/equinox) offering full autograd support, easy extension with custom neuron dynamics, and built-in delay training.

## Features
- Fully differentiable implementation via JAX and Diffrax
- Easy extension with custom neuron model dynamics + learnable parameters
- Support for (trainable) synnaptic delays.
- GPU/TPU compatibility through JAX

## 📦 Installation
```bash
pip install eventax
```
