https://github.com/ahmad-ali-rafique/handwritten-digit-recognition-mnist

This project demonstrates a complete pipeline for recognizing handwritten digits using the MNIST dataset. The project is implemented in Python using Jupyter Notebook, and it covers data loading, preprocessing, model training, and performance evaluation of a Fully Connected Neural Network (FCNN).
https://github.com/ahmad-ali-rafique/handwritten-digit-recognition-mnist

ai artificial-intelligence data data-analysis datascience deep-learning deep-neural-networks fcnn fully-connected-network machine-learning machine-learning-algorithms ml modeling

Last synced: 2 days ago
JSON representation

This project demonstrates a complete pipeline for recognizing handwritten digits using the MNIST dataset. The project is implemented in Python using Jupyter Notebook, and it covers data loading, preprocessing, model training, and performance evaluation of a Fully Connected Neural Network (FCNN).

• Host: GitHub
• URL: https://github.com/ahmad-ali-rafique/handwritten-digit-recognition-mnist
• Owner: Ahmad-Ali-Rafique
• Created: 2024-06-15T05:16:00.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-06-15T07:37:40.000Z (5 months ago)
• Last Synced: 2024-06-16T06:30:02.698Z (5 months ago)
• Topics: ai, artificial-intelligence, data, data-analysis, datascience, deep-learning, deep-neural-networks, fcnn, fully-connected-network, machine-learning, machine-learning-algorithms, ml, modeling
• Language: Jupyter Notebook
• Homepage:
• Size: 5.15 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
![Your Picture](https://github.com/Ahmad-Ali-Rafique/Handwritten-Digit-Recognition-MNIST/blob/main/MnistExamplesModified.png)

# Handwritten Digit Recognition using MNIST Dataset with a Fully Connected Neural Network (FCNN)

## Overview

This project demonstrates a complete pipeline for recognizing handwritten digits using the MNIST dataset. The project is implemented in Python using Jupyter Notebook, and it covers data loading, preprocessing, model training, and performance evaluation of a Fully Connected Neural Network (FCNN).

## Project Description

The project uses the MNIST dataset, which consists of 70,000 images of handwritten digits (0-9) split into training and testing sets. The pipeline includes:

1. **Data Loading**: Loading the MNIST dataset from a public source.

2. **Data Preprocessing**: Normalizing and reshaping the images to be suitable for the FCNN model.

3. **Model Training**: Building and training a Fully Connected Neural Network using TensorFlow/Keras.

4. **Performance Evaluation**: Evaluating the model's accuracy and loss on the test set, and visualizing the results.

### Key Features

- **Data Preprocessing**: Techniques such as normalization and reshaping for optimal model performance.

- **Model Architecture**: Details of the FCNN layers, activation functions, and optimization techniques.

- **Evaluation Metrics**: Accuracy, loss, confusion matrix, and visualizations to assess the model's performance.

## About Me

Hi, I'm Ahmad Ali, a passionate data scientist and machine learning enthusiast with a knack for solving complex problems using data-driven approaches. I have a strong background in data science and artificial intelligence, and I enjoy working on projects that involve deep learning, computer vision, and natural language processing.

### Get in Touch

- **LinkedIn**: [https://www.linkedin.com/in/yourprofile](https://www.linkedin.com/in/ahmad-ali-rafique/)

- **Email**: [email protected]