Metadata-Version: 2.1
Name: simple-neural-net
Version: 0.1.0
Summary: Minimal framework for creating a simple neural net
Home-page: https://github.com/tcquinn/simple-neural-net
Author: Theodore Quinn
Author-email: tcquinn@tcquinn.org
License: UNKNOWN
Keywords: neural network,deep learning
Platform: UNKNOWN
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Requires-Dist: numpy (>=1.18)
Requires-Dist: tqdm (>=4.46)

# simple_neural_net

Minimal framework for creating a simple neural net

## Installation

`pip install simple-neural-net`

## Tasks
  * Consider changing shape of X and y inputs to match `sklearn` conventions
  * Add method which automatically evaluates model accuracy
  * Add cost model and prediction model for multi-class classification
  * Add other layer geometries (will require splitting up `Layer` class)
  * Add batching


