ELEC 425 Machine Learning and Deep Learning Units: 3.50
Supervised and unsupervised machine learning methods for regression, classification, clustering, and time series modeling. Methods of fitting models. The problem of overfitting and techniques for addressing it. Deep learning and neural network models. Processes for how to refine/ implement/ test applications of machine/deep learning algorithms.
(Lec: 3, Lab: 0.25, Tut: 0.25)
(Lec: 3, Lab: 0.25, Tut: 0.25)
Requirements: Prerequisites: ELEC 278 or CISC 235 or MREN 178, ELEC 326 or permission of the instructor
Corequisites:
Exclusions: CMPE 452
Offering Term: W
CEAB Units:
Mathematics 11
Natural Sciences 0
Complementary Studies 0
Engineering Science 20
Engineering Design 11
Offering Faculty: Smith Engineering
Course Learning Outcomes:
- Demonstrate understanding of basic supervised and unsupervised machine learning models.
- Demonstrate learning of regression, classification, clustering, and time series modelling.
- Demonstrate the understanding of basic architectures of deep learning models.
- Develop skills in designing and implementing basic machine learning and deep learning models.
- Develop the basic ability to use popular machine learning and deep learning environments.