https://github.com/mathensley/asimpleneuralnetworklib

A simple library in Python for training datasets using neural network models
https://github.com/mathensley/asimpleneuralnetworklib

deep-learning neural-networks numpy python

Last synced: 11 months ago
JSON representation

A simple library in Python for training datasets using neural network models

• Host: GitHub
• URL: https://github.com/mathensley/asimpleneuralnetworklib
• Owner: mathensley
• Created: 2024-11-17T18:14:33.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-20T15:58:16.000Z (about 1 year ago)
• Last Synced: 2025-01-26T15:28:57.341Z (about 1 year ago)
• Topics: deep-learning, neural-networks, numpy, python
• Language: Python
• Homepage:
• Size: 14.6 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# A Simple Neural Network Library for Python

## Overview

This is a simple library I created as part of my studies in deep learning and machine learning. The main goal was to practice key concepts like model initialization, forward propagation, backward propagation, and optimization techniques. It currently supports three models:

1. **Logistic Regression Model**

2. **Two-Layer Neural Network Model**

3. **N-Layer Neural Network Model**

**Note**: The library is in an experimental stage and is specifically designed for binary classification problems. A few features for possible future updates:

- Saving and loading model parameters.

- Support for custom activation functions and loss functions.

- GPU support using libraries like PyTorch or TensorFlow.

## Prerequisites

Before installing, ensure you have the following:

- **Python** (Version 3.6 or higher)

- **pip**

- **NumPy**

## Installation

To install the library directly from the GitHub repository, use the following command:

```bash

pip install git+https://github.com/mathensley/ASimpleNeuralNetworkLib.git