Interactive Neural Network Classifier with Streamlit

This project is an interactive deep learning web application built with Streamlit that demonstrates how neural networks learn and make predictions. It was designed to be both an educational tool and a practical demonstration of supervised learning in action.

Key features of the application include:

Model Customization: Users can experiment with different hyperparameters such as the number of hidden layers, activation functions, and learning rates.

Real-Time Training & Visualization: The app trains the model live and displays performance metrics (accuracy, loss curves, decision boundaries) as the parameters change.

Hands-On Learning: By adjusting parameters, users can directly observe how these changes affect the network’s ability to classify data.

User-Friendly Interface: Built with Streamlit for simplicity and accessibility, making it easy for anyone to explore deep learning concepts without prior coding experience.

This project highlights practical skills in Python, TensorFlow/Keras, machine learning, and web app deployment. It not only demonstrates the power of neural networks but also makes complex AI concepts accessible through interactivity and visualization.