Student's Portal

The Course Will Present Advanced Topics in Machine Learning That Emerge From Current Deep Learning Architectures, Emphasizing Their Ability to Fit to a Training Sample and Their Generalization Capability As Well As Generative Learning of Data From Learned Probability Distribution. Learning Outcomes# at The End of The Course The Students Will Be Able To# - Develop and Execute Neural Nets. - Develop and Execute Convolutional Neural Nets. - Run Learning Pipeline of Train/validation/test Including A/b Testing - Evaluate Overfitting. - Mitigate Overfitting and Identify Generalization.

Faculty: Data and Decision Sciences
|Graduate Studies

Pre-required courses

96411 - Machine Learning 1

Course with no extra credit

46211 - Deep Learning 236781 - Deep Learning On Computation

Course with no extra credit (contains)

46217 - Deep Learning