Metadata-Version: 2.4
Name: axonet
Version: 0.1.4
Summary: Neural network experiment utilities
License: MIT
License-File: LICENSE
Keywords: mlp,neural-network,pytorch
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Provides-Extra: all
Requires-Dist: datasets; extra == 'all'
Requires-Dist: evaluate; extra == 'all'
Requires-Dist: librosa; extra == 'all'
Requires-Dist: torchaudio; extra == 'all'
Requires-Dist: transformers; extra == 'all'
Provides-Extra: audio
Requires-Dist: librosa; extra == 'audio'
Requires-Dist: torchaudio; extra == 'audio'
Provides-Extra: hf
Requires-Dist: datasets; extra == 'hf'
Requires-Dist: evaluate; extra == 'hf'
Requires-Dist: transformers; extra == 'hf'
Description-Content-Type: text/markdown

# axonet

Utilities for neural network experiments.

A neural network is composed of layers of artificial neurons (loosely modeled after biological neurons connected by axons and synapses). Each neuron applies a learnable linear transformation followed by a nonlinearity. Modern architectures — feedforward, convolutional, recurrent, and transformer — all build on this core mechanic.

## Install

```
pip install axonet
```
