Education

Problem-solving and planning; state/action models and graph searching. Natural language understanding Computational vision. Applications of artificial intelligence.

Application of machine learning tools, with an emphasis on solving practical problems. Data cleaning, feature extraction, supervised and unsupervised machine learning, reproducible workflows, and communicating results.

We introduce basic principles and techniques in the fields of data mining and machine learning. These are some of the key tools behind the emerging field of data science and the popularity of the `big data’ buzzword. These techniques are now running behind the scenes to discover patterns and make predictions in various applications in our daily lives. We’ll focus on many of the core data mining and machine learning technlogies, with motivating applications from a variety of disciplines.

Principles and techniques underlying the design, implementation and evaluation of intelligent computational systems. Applications of artificial intelligence to natural language understanding, image understanding and computer-based expert and advisor systems. Advanced symbolic programming methodology.

Introduction to the processing and interpretation of images. Image sensing, sampling, and filtering. Algorithms for colour analysis, texture description, stereo imaging, motion interpretation, 3D shape recovery, and recognition.

Advanced machine learning techniques focusing on probabilistic models. Deep learning and differentiable programming, exponential families and Bayesian inference, probabilistic graphical models and other generative models, Monte Carlo and variational inference methods.

Artificial intelligence, machine learning techniques, Deep learning, Python libraries for machine learning, Basic signal processing techniques, Data Acquisition, Applications in Manufacturing, Use of sound to evaluate operation of CNC machinery, Use of AE sensor to evaluate metal 3D printing.

This course is about learning to control the movement of humans, animals, and robots, with application to character animation, computer vision, robotics, and biological motor control. Much of the course will focus on (deep) reinforcement learning, which has seen many advances over the past 5 years.

Topics include kinematic and dynamic models of motion, basics of physics-based simulation, classical control methods, dynamic programming, and deep reinforcement learning. Background material will be introduced as necessary. Prior experience in computer graphics, robotics, introductory reinforcement learning, and deep learning will be helpful, but is not necessary.

This is an graduate (or senior undergraduate) course on machine learning, a field that focuses on using automated data analysis for tasks like pattern recognition and prediction. The course will move quickly and assumes a strong background in math and computer science as well as previous experience with statistics and/or machine learning. The class is intended as a continuation of CPSC 340/532M and it is strongly recommended that you take CPSC 340/532M first before enrolling in CPSC 540. Topics will (roughly) include deep learning, Markov models, latent-variable models, probabilistic graphical models, and Bayesian methods.