Skip to content

Letter Recognition using a neural network to classify images with custom algorithms • Built a feedforward neural network using NumPy to classify binary images of letters A, B, and C • Implemented custom backpropagation and sigmoid activation, tracking model accuracy and visualizing predictions using Matplotlib

Notifications You must be signed in to change notification settings

SarthakKumarPathak/neural-network-classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 

Repository files navigation

Neural Network Classifier 🧠🔤

License: MIT

Overview 📚

This project focuses on letter recognition using a custom-built feedforward neural network. It classifies binary images of letters A, B, and C using NumPy for computation and Matplotlib for visualizations. From scratch, the network implements forward propagation, sigmoid activation, and custom backpropagation, offering insights into the workings of neural networks.


Key Features 🚀

  • 🏗️ Built a feedforward neural network entirely from scratch using NumPy.
  • 🔁 Implemented custom backpropagation and sigmoid activation without any ML libraries.
  • 🧮 Trained on binary image datasets of letters A, B, and C.
  • 📊 Tracked training accuracy over epochs to evaluate performance.
  • 📉 Visualized model predictions and training results using Matplotlib.

Technologies & Tools 🛠️

  • Python
  • NumPy
  • Matplotlib
  • Object-Oriented Programming

How to Run ▶️

  1. Clone the repository:
    git clone https://github.com/SarthakKumarPathak/neural-network-classifier.git
  2. Install dependencies: (All required libraries are standard in most Python environments): pip install numpy matplotlib
  3. Run the training script: python train_classifier.py

Results & Visualizations 📈

Achieved high classification accuracy on the letter dataset.

Visualized training performance with plots of accuracy vs. epochs.

Displayed predictions vs. actual labels to showcase classifier performance.

License 📄

This project is licensed under the MIT License - see the LICENSE file for details.

Made with ❤️ by Sarthak Kumar Pathak

About

Letter Recognition using a neural network to classify images with custom algorithms • Built a feedforward neural network using NumPy to classify binary images of letters A, B, and C • Implemented custom backpropagation and sigmoid activation, tracking model accuracy and visualizing predictions using Matplotlib

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published