🤖 Machine Learning Projects

A comprehensive collection of 13 machine learning projects showcasing expertise in supervised learning, unsupervised learning, deep learning, NLP, computer vision, and reinforcement learning.

---

🎯 Featured Project Highlights

Neural Network Learning Visualization (MNIST Digit Classifier)

Watch how the neural network learns to recognize handwritten digits! The weight matrices evolve from random noise to meaningful patterns:

Before Training	After Training
Random weight initialization	Learned digit patterns emerge

Image Colorization with Deep Learning

Transforming grayscale images into vibrant, colorized versions using neural networks:

AI-generated colorization of a grayscale image

---

📂 Projects Overview

🔮 Deep Learning & Neural Networks

Project	Description	Key Technologies
MNIST Digit Classifier	Training neural networks to classify handwritten digits with weight visualization	TensorFlow, Keras
Coloring Black & White Images	Deep learning models to add color to grayscale images	OpenCV, Deep Learning
Fraud Detection using ANN	Analyzing bank customer data using ANN and Self-Organizing Maps	Keras, Minisom
Stock Prediction using RNN	Forecasting stock prices using LSTM networks	TensorFlow, LSTM
Fruit Classification	Transfer learning with VGG16 for multi-class fruit classification (84% accuracy)	TensorFlow, VGG16, Transfer Learning

📊 Classification & Regression

Project	Description	Key Technologies
Customer Purchase Classification	Predicting customer purchases using 6 different ML algorithms	SVM, KNN, Random Forest, Naive Bayes
Salary Prediction	Regression models to predict employee salaries	Linear, Polynomial, SVR, Random Forest
Weather Prediction	Predicting rainfall in Australian cities using classification models	Random Forest, Logistic Regression, GridSearchCV

🎯 Clustering & Unsupervised Learning

Project	Description	Key Technologies
Customer Segmentation	Segmenting mall customers using clustering techniques	K-Means, Hierarchical Clustering
Movie Rating Prediction	Predicting movie preferences using Autoencoders and Boltzmann Machines	PyTorch, Autoencoders, RBM

💬 NLP & Language Models

Project	Description	Key Technologies
Natural Language Processing	Sentiment classification of restaurant reviews	NLTK, Random Forest, Maximum Entropy
PPO Fine-Tuning for Sentiment	Training "Happy" and "Pessimistic" LLMs using Proximal Policy Optimization	TRL, Transformers, PPO, RLHF
RAG QA Bot	Document-based Q&A chatbot using Retrieval-Augmented Generation	LangChain, Ollama, ChromaDB, Streamlit

---

🛠️ Technologies & Tools

Languages & Frameworks Python - Primary language TensorFlow / Keras - Deep learning PyTorch - Neural networks Scikit-learn - Traditional ML

Data & Visualization Pandas / NumPy - Data manipulation Matplotlib / Seaborn - Visualization OpenCV / PIL - Image processing

Specialized Tools NLTK - NLP LangChain - LLM applications Minisom - Self-organizing maps XGBoost - Gradient boosting

---

📈 Project Metrics

Category	Count	Examples
🧠 Deep Learning	5	MNIST, RNN Stock Prediction, Fruit Classification
📊 Classification	3	Customer Purchases, Weather, NLP
📉 Regression	1	Salary Prediction
🎯 Clustering	2	Customer Segmentation, Movie Ratings
💬 NLP/LLM	2	PPO Fine-Tuning, RAG QA Bot

---

🚀 Getting Started

# Clone the repository
git clone https://github.com/Medyan-Naser/machine_learning_projects.git

# Navigate to a project
cd machine_learning_projects/<project-folder>

# Install dependencies (example)
pip install -r requirements.txt

# Run the project
python <script_name>.py

---

📄 Documentation

Detailed documentation for each project is available in the docs folder, including:

• Algorithm explanations
• Implementation details
• Results and analysis

---

📧 Contact

Feel free to explore the projects and reach out with any questions or feedback!