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:

Courses ELG 5255 , CSI 5155 , DTO 5100 , DTO 5101 , IAI 5100 , IAI 5101 , MIA 5100 , SYS 5185 cannot be combined for units.

Previously Offered Terms:

Fall
Winter
Summer
All Professors
A Average (9.338)
Most Common: A+ (53%)
275 students

P

S

NS

F

D

C

B

A-

A+

Unknown Professor

Winter 2024 - W00

A Average (9.480)
Most Common: A+ (52%)
25 students

P

S

NS

F

D

C

B

A-

A+

Hitham Jleed

Fall 2023 - F00

A- Average (8.296)
Most Common: A+ (33%)
27 students

P

S

NS

F

D

C

B

A-

A+

Murat Simsek

3 sections from Summer 2022 to Summer 2023

A Average (9.448)
Most Common: A+ (55%)
223 students

P

S

NS

F

D

C

B

A-

A+