AI & Machine Learning Projects

Welcome to the repository for my AI and Machine Learning projects. This repository contains all the work completed during a hands-on introduction to machine learning and artificial intelligence using Python, Scikit-Learn, TensorFlow, and Keras.

Course Overview

This course provides an in-depth, hands-on experience with the full machine learning workflow, including:

• Data Preprocessing & Feature Engineering
• Classical Machine Learning Algorithms (e.g., Linear Regression, SVM, Decision Trees)
• Deep Neural Networks (e.g., Feedforward Neural Networks, CNNs, RNNs)
• Advanced Models (e.g., GANs, Reinforcement Learning)

By working with these models, students learn the essential techniques to build and optimize AI solutions, from raw data to intelligent decision-making systems.

Projects

The following sections include the key projects from this course:

1. Data Preprocessing & Feature Engineering

• Overview: Techniques for preparing raw data and extracting meaningful features for machine learning models.
• Tools: Pandas, Scikit-Learn
• Description: Cleaned and transformed datasets, performed feature scaling, and handled missing data.

2. Classical Machine Learning Algorithms

• Overview: Implemented traditional machine learning models such as Linear Regression, K-Nearest Neighbors, Support Vector Machines, etc.
• Tools: Scikit-Learn
• Description: Built and evaluated models on real-world datasets.

3. Neural Networks (NN)

• Overview: Constructed fully connected neural networks for regression and classification tasks.
• Tools: TensorFlow, Keras
• Description: Designed and trained multi-layer perceptron models on complex datasets.

4. Convolutional Neural Networks (CNNs)

• Overview: Created CNNs for image classification tasks.
• Tools: TensorFlow, Keras
• Description: Implemented various CNN architectures for image recognition tasks.

5. Recurrent Neural Networks (RNNs)

• Overview: Built RNNs for time series forecasting and sequence prediction tasks.
• Tools: TensorFlow, Keras
• Description: Trained models to process sequential data, such as text or time series.

6. Generative Adversarial Networks (GANs)

• Overview: Developed GANs for generating realistic images.
• Tools: TensorFlow, Keras
• Description: Built and trained models to generate new data samples, such as images, from random noise.

7. Reinforcement Learning (RL)

• Overview: Implemented reinforcement learning algorithms for decision-making in dynamic environments.
• Tools: TensorFlow, OpenAI Gym
• Description: Trained agents using Q-learning, Deep Q Networks, and Policy Gradient methods.