https://github.com/mariam-badr-mb/mnist-classification
A simple neural network to classify handwritten digits from the MNIST dataset. Build model with activation functions.
https://github.com/mariam-badr-mb/mnist-classification
deep-learning jypyternotebook keras-tensorflow mnist-classification neural-network python
Last synced: 2 months ago
JSON representation
A simple neural network to classify handwritten digits from the MNIST dataset. Build model with activation functions.
- Host: GitHub
- URL: https://github.com/mariam-badr-mb/mnist-classification
- Owner: Mariam-Badr-MB
- License: gpl-3.0
- Created: 2025-07-24T21:49:36.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-07-24T22:01:02.000Z (3 months ago)
- Last Synced: 2025-07-25T03:26:57.806Z (3 months ago)
- Topics: deep-learning, jypyternotebook, keras-tensorflow, mnist-classification, neural-network, python
- Language: Jupyter Notebook
- Homepage:
- Size: 62.5 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 🧠 MNIST Digit Classification Using Neural Networks
This project builds and trains neural networks on the **MNIST dataset** to classify handwritten digits (0–9).
---## 💡 Objective
Explore how activation functions and regularization affect neural network performance in digit classification.
---
## 📊 Techniques Used
- **Data Preprocessing**:
- Normalize pixel values
- One-hot encode labels
- **Build Model **:
- With activation functions
- **Loss & Accuracy Visualization**---
## 🧠 Tools & Libraries
- Python
- `TensorFlow`, `Keras`
- `NumPy`, `Matplotlib`---
## 📁 Dataset
- Dataset: **MNIST Handwritten Digits**
- 60,000 training images and 10,000 test images of digits (0–9)
- Each image is 28x28 pixels in grayscale
- Loaded directly from `keras.datasets.mnist`---
## 📈 Project Workflow
1. **Load & Preprocess Data**
2. **Build Model with Activation**
3. **Train The Model**
4. **Evaluate Final Model**
5. **Visualize Predictions**---
## 🔍 Example Output
- Accuracy Comparison of Models
- Training vs. Validation Loss Plot
- Sample Predictions with True Labels---
## 💾 Output Sample
| Image Index | True Label | Predicted Label |
|-------------|------------|-----------------|
| 0 | 7 | 7 |
| 1 | 2 | 2 |
| 2 | 1 | 1 |---
## 👩💻 Author
**Mariam Badr**
Faculty of Computers & Artificial Intelligence, Cairo University
[GitHub](https://github.com/Mariam-Badr-MB) – [LinkedIn](https://www.linkedin.com/in/mariambadr13/)---
## 📜 License
This project is for educational and learning purposes only.