Description
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.
Posting limited to :
Professeur à temps-partiel régulier / Regular Part-Time Professor
Date Posted : May 07, 2024
May 07, 2024
Closing Date : June 10, 2024
June 10, 2024
Note : Applications will be accepted until 11 : 59 PM on the day prior to the Posting End Date above
Expected Enrolment : n / a
n / a
Approval date : May 07, 2024
May 07, 2024
Number of credits : Work Hours :
Work Hours : Course type :
Course type : Posting type :
Posting type : Régulier / Regular
Régulier / Regular
Language of instruction :
Anglais English
Competence in second language :
Passive
Course Schedule :
Mardi Tuesday 14 : 30-17 : 30 - -
Requirements :
Expert knowledge of the course subject matter, demonstrated by relevant research publications or extensive experience over at least two years, or having taught related courses previously.
Applicants must have a doctorate and it should be in the field related to the course subject matter, or the candidate must have worked professionally in the field after their doctorate.
Additional Information
Please note that the teaching method for this course will be delivered : in person.
Additional Information and / or Comments :
An acceptable level of education and / or experience could be viewed as being equivalent to the educational required and / or demonstrated experience.