Applied Machine Learning

Catalog description

Machine learning enables computers to learn patterns from data and make predictions or decisions without being explicitly programmed. This course provides a comprehensive introduction to machine learning methods and their practical applications, with an emphasis on modern deep learning techniques. The course begins with fundamental machine learning concepts and traditional methods, including regression and logistic regression. It then focuses on advanced deep learning approaches, covering neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs) and LSTMs, attention mechanisms, sequence-to-sequence modeling, and transformer-based architectures such as GPT-style models. Additional topics include generative models (e.g., GANs), anomaly detection, meta-learning, and deep reinforcement learning. Through hands-on programming assignments and projects, students will gain practical experience implementing machine learning and deep learning models and applying them to real-world datasets. The goal of the course is to equip students with both the theoretical understanding and practical skills necessary to design, train, and evaluate modern machine learning systems for real-world applications. Prerequisite: INFO 501 and INFO 535. INFO 505 may be taken concurrently. Typically offered at least once every two years.