Mathematics 697PA - ST-Math Foundtns/ProbabilistAI
Fall
2020
01
3.00
Markos Katsoulakis;Luc Rey-Bellet
TU TH 10:00AM 11:15AM
UMass Amherst
68505
Fully Remote Class
markos@math.umass.edu;luc@math.umass.edu
The course will primarily focus on the mathematical foundations of probabilistic Artificial Intelligence. The topics covered will include: Fundamentals of Information Theory, Markov Chain Monte Carlo Approximate Inference and Variational Inference Graphical Models (directed and undirected) Hidden Markov Models
Neural Networks and other Black Box methods Support Vector Machines
Adversarial learning, Game Theory and Generative Adversarial Networks, Reinforcement Learning Sensitivity Analysis, Uncertainty Quantification.
Neural Networks and other Black Box methods Support Vector Machines
Adversarial learning, Game Theory and Generative Adversarial Networks, Reinforcement Learning Sensitivity Analysis, Uncertainty Quantification.
The course will primarily focus on the mathematical foundations of probabilistic Artificial Intelligence.
The topics covered will include: Fundamentals of Information Theory, Markov Chain Monte Carlo
Approximate Inference and Variational Inference
Graphical Models (directed and undirected)
Hidden Markov Models
Neural Networks and other Black Box methods
Support Vector Machines
Adversarial learning, Game Theory and Generative Adversarial Networks,
Reinforcement Learning
Sensitivity Analysis, Uncertainty Quantification
The topics covered will include: Fundamentals of Information Theory, Markov Chain Monte Carlo
Approximate Inference and Variational Inference
Graphical Models (directed and undirected)
Hidden Markov Models
Neural Networks and other Black Box methods
Support Vector Machines
Adversarial learning, Game Theory and Generative Adversarial Networks,
Reinforcement Learning
Sensitivity Analysis, Uncertainty Quantification