Skip to content

YsK-dev/MnistFromScrtath

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

MNIST From Scratch

🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼🐼

Achieving 89% accuracy on the MNIST dataset with a custom implementation is just amazing!

Accuracy

Model Predictions

Model Predictions 1 Model Predictions 2 Model Predictions 3

Introduction

This project demonstrates a simple yet effective implementation of a neural network trained from scratch to classify handwritten digits from the MNIST dataset. Achieving an accuracy of 89% showcases the potential of custom-built models and the power of understanding machine learning fundamentals.

Features

  • Custom Neural Network Implementation: Built from scratch without using high-level libraries.
  • High Accuracy: Achieved 89% accuracy on the MNIST test dataset.
  • Model Visualization: Clear visual examples of the model’s predictions on test data.

Installation

To run this project, ensure you have Python installed along with the necessary dependencies. You can install the required packages and just run the code

Data

I Used Mnist data set which is amazing 🔢

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published