Machine Learning Lab

A comprehensive collection of machine learning algorithms, techniques, and implementations for educational and practical purposes.

---

Overview

This repository contains various machine learning implementations and examples ranging from classic reinforcement learning (Q-Learning) to advanced deep learning techniques (CNN, LSTM, GAN, GNN). Each directory focuses on a specific algorithm or concept with practical examples and visualizations.

---

Repository Structure

1. Q Learning

• Implementation of Q-Learning reinforcement learning algorithm
• Visualization of Q-Learning process

2. Multilayer Perceptron (MLP)

• Univariate MLP implementation
• Multivariate MLP implementation
• Multi-step prediction MLP
• Combined multivariate multi-step MLP

3. Neural Network

• Basic neural network implementation

4. Convolutional Neural Networks (CNN)

• CNN implementation with optimized training
• Training history visualization

5. Image to CSV

• Tool to extract text from images and convert to CSV format

6. Hyperparameter Optimization for LSTM

• Implementation of hyperparameter tuning for LSTM models
• Results visualization and best parameters selection

7. Graph Neural Networks (GNN)

• Implementation of Graph Neural Networks
• Includes Cora dataset for node classification

8. Numpy and Tensorflow Basics

• Basic operations and examples using NumPy
• TensorFlow tensor operations and shape manipulations

9. Generative Adversarial Networks (GAN)

• Implementation of GAN architecture

10. Datasets

• Electric production dataset
• Synthetic time series dataset

11. Final Exam Lab Code

• MLPwithHyperparameter: Multilayer perceptron with hyperparameter tuning
• predicWeatherLSTM: LSTM model for weather prediction
• numpy_folder: Basic NumPy operations
• Various datasets for experimentation

---

Getting Started

Prerequisites

• Python 3.6+
• TensorFlow 2.x
• PyTorch
• NumPy
• Pandas
• Matplotlib
• Scikit-learn

Installation

# Clone this repository
git clone https://github.com/nishatrhythm/Machine-Learning-Lab.git

# Navigate to the repository directory
cd Machine-Learning-Lab

# Install required packages
pip install -r requirements.txt  # Note: Create this file with the necessary dependencies

---

Usage Examples

Each directory contains specific implementations with their own usage instructions. Below are a few examples:

Q Learning

# Run Q Learning algorithm
python "1. Q Learning/Q_Learning.py"

Neural Network

# Run basic neural network implementation
python "3. Neural Network/neuralNetwork.py"

CNN

# Run CNN implementation
python "4. CNN/cnn.py"

---

Acknowledgments

• Various open-source machine learning libraries and tools
• Academic resources and tutorials that inspired these implementations