AIML 2220 - Foundations of Machine Learning

Prerequisites: DSCI 3212 and CSCI 2226 or AIML 2226. This course offers foundations on machine learning paradigms, statistical pattern recognition techniques, and practical system design considerations. The curriculum begins with supervised learning and techniques for model refinement like regularization and general classification. It then delves into unsupervised learning and dimensionality reduction through Factor Analysis, Principal Component Analysis (PCA), and anomaly detection. The course also covers advanced topics in Neural Networks, weakly supervised/unsupervised learning, and Reinforcement Learning (RL). A significant emphasis is placed on applied challenges, specifically ML system design, large-scale ML deployments, recommender systems, and a critical examination of the societal impact and ethical considerations of intelligent systems. Students will gain the theoretical understanding and practical framework necessary to analyze, design, and deploy robust ML solutions. 3 credits.