NNWeaver’s Documentation

NNWeaver is a tiny Python library to create and train feedforward neural networks. We developed this library as a project for a Machine Learning course.

Some of its features are:

1. Simple API, easy to learn.
2. Validation functions included.
3. Lightweight and with few dependencies.
4. Live loss/epoch curve display.

Table of Contents

• Getting Started
  • Specify a Neural Network Topology
  • Train the Neural Network
  • Validate a Model
  • Other (Cool) Stuff
• Tuning Hyperparameters
• API Reference
  • nnweaver.activations module
  • nnweaver.callbacks module
  • nnweaver.losses module
  • nnweaver.nn module
  • nnweaver.optimizers module
  • nnweaver.regularizers module
  • nnweaver.utils module
  • nnweaver.validation module
• Index

Inheritance diagram