ITCS 8156 - Machine Learning

Introduction to advanced concepts, techniques, and algorithms underlying the theory and practice of machine learning (ML) and deep learning. The description of the formal properties of the algorithms will be supplemented with motivating applications in areas such as natural language processing, computer vision, education, or medicine. Topics include: bias-variance trade-off; ensemble methods; autoencoders, convolutional neural networks, (gated) recurrent neural networks and attention; Transformer and language models; probabilistic graphical models and structured outputs; energy-based models, GANs, VAEs, and diffusion; time series forecasting; explainability and probing of ML models; bias in ML models; theoretical underpinnings of deep learning; deep reinforcement learning (RL).

Credit Hours: (3)

Schedule of Classes