ELG 5255 Applied Machine Learning
3 units
Electrical Engineering
Faculty of Engineering
Machine learning is an effective tool to design systems that learn from experience and adapt to an environment. Theory and applications of machine learning to the design of electrical and computer systems, devices and networks by using techniques that utilize statistics, neural computation and information theory. Fundamentals of supervised learning, Bayesian estimation, clustering and unsupervised learning, multivariate, parametric and non-parametric methods, kernel machines, hidden Markov models, multilayer perceptron networks and deep neural networks, ensemble learning and reinforcement learning. Design and testing of machine learning techniques integrated into real-world systems, devices and networks. Guidelines for machine learning experiments, methods for cross-validation and resampling, classifier performance analysis and tools for comparing classification algorithms and analysis of variance to compare multiple algorithms.
Components:
Lecture
Requirements:
Previously Offered Terms:
Fall
Winter
Summer
All Professors
A Average (9.338)
Most Common: A+ (53%)
275 students
F
D
C
B
A-
A+
Unknown Professor
Winter 2024 - W00
A Average (9.480)
Most Common: A+ (52%)
25 students
F
D
C
B
A-
A+