Metadata-Version: 2.1
Name: lfprop
Version: 0.1.0
Summary: A package for gradient-free neural network training using LFP
License: BSD-3-Clause
Keywords: explainable ai,xai,machine learning,deep learning,gradient-free optimization
Author: Leander Weber
Author-email: leander.weber@hhi.fraunhofer.de
Maintainer: Leander Weber
Maintainer-email: leander.weber@hhi.fraunhofer.de
Requires-Python: >=3.11
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Provides-Extra: full
Provides-Extra: quickstart
Requires-Dist: joblib (>=1.4.2,<2.0.0) ; extra == "full"
Requires-Dist: lxt (>=0.6.1,<0.7.0)
Requires-Dist: matplotlib (<3.8) ; extra == "full"
Requires-Dist: notebook (>=7.3.2,<8.0.0) ; extra == "quickstart" or extra == "full"
Requires-Dist: pandas (>=2.2.3,<3.0.0) ; extra == "full"
Requires-Dist: scikit-learn (>=1.6.1,<2.0.0) ; extra == "full"
Requires-Dist: torcheval (>=0.0.7,<0.0.8) ; extra == "quickstart" or extra == "full"
Requires-Dist: wandb (>=0.19.4,<0.20.0) ; extra == "full"
Requires-Dist: zennit (>=0.5.1,<0.6.0)
Description-Content-Type: text/markdown

# Layer-wise Feedback Propagation

Gradient-free Neural Network Training based on Layer-wise Relevance Propagation (LRP)

### :octopus: Flexibility
LFP does not require differentiable models or objectives. 

### :gear: Efficiency


### :open_book: Paper


### :scroll: License


## :rocket: Getting Started


### :fire: Installation

LFP is available from PyPI, to install simply run

```shell
$ pip install lfp
```

### Overview


### Examples


### :mag: Reproducing Experiments

To reproduce experiments from the paper


## :pencil2: Contributing
