Introduction to Artificial Intelligence & Machine Learning

A complete, practical, beginner-to-intermediate course in Artificial Intelligence and Machine Learning: what AI actually is and how it evolved; Python programming fundamentals; NumPy, Pandas and data visualization; understanding, collecting, cleaning, and engineering data; the full machine-learning vocabulary and workflow; supervised learning (linear/logistic regression, decision trees, random forests, KNN, SVM); model evaluation (accuracy, confusion matrices, precision/recall, over/underfitting); unsupervised learning (clustering, K-Means, PCA); the standard Scikit-Learn workflow; feature engineering, cross-validation and hyperparameter tuning; an introduction to deep learning and neural networks; TensorFlow/Keras; computer vision and CNNs; Natural Language Processing and sentiment analysis; chatbots; Generative AI, LLMs and prompt engineering; Transformers; AI ethics and responsible AI; taking an AI project from idea to deployed application; and 7 guided projects culminating in a capstone AI-powered application. Learning by doing throughout: students write Python code, work with real datasets, train and evaluate models, build neural networks, and complete practical projects.