# Neural Network for Image Classification using MNIST Dataset

**Technologies:** Python, Keras  

## Objective
This project aims to create a neural network that classifies images from the MNIST dataset, offering foundational experience in deep learning and image classification.

## Key Contributions
- Developed a feed-forward neural network using Keras to accurately classify images of handwritten digits from the MNIST dataset.
- Preprocessed image data by normalizing pixel values, which improved the efficiency and accuracy of model training.
- Evaluated model performance, achieving high accuracy through hyperparameter tuning, including adjustments to learning rate, batch size, and model architecture.

## Outcome
The neural network achieved over 90% accuracy on the MNIST dataset, demonstrating effective implementation and training of a neural network for image classification tasks.

For more details, check out the project on GitHub: [Neural Network for Image Classification using MNIST Dataset](https://github.com/mrw-soumik/Neural-Network-for-Image-Classification-using-MNIST-Dataset/tree/main)