Difference between revisions of "MAT5YYY"
Jump to navigation
Jump to search
Jose.iovino (talk | contribs) |
Jose.iovino (talk | contribs) |
||
| Line 13: | Line 13: | ||
''Content'': | ''Content'': | ||
Vectors, matrices and tensors; discrete and continuous probability; random variables and expectation; elements of information theory; basic methods for probabilistic learning (maximum likelihood, Bayesian statistics); supervised and unsupervised learning algorithms; neural networks: feedforward, convolutional, recurrent/recursive; loss functions and gradient-based learning; optimization and regularization methods; algorithm implementations; testing on real-world datasets. | Vectors, matrices and tensors; discrete and continuous probability; random variables and expectation; elements of information theory; basic methods for probabilistic learning (maximum likelihood, Bayesian statistics); supervised and unsupervised learning algorithms; neural networks: feedforward, convolutional, recurrent/recursive; loss functions and gradient-based learning; optimization and regularization methods; algorithm implementations; testing on real-world datasets. | ||
| − | |||
| − | |||
| − | |||
Latest revision as of 18:03, 24 March 2026
Mathematics of AI - MAT4YYY/5YYY
Catalog description
Prerequisites: Prerequisites: MAT2233 Linear Algebra, or MAT 253 Applied Linear Algebra; STA3513 Probability and Statistics MAT2213 Calculus 3 CS 1063 Introduction to Computer Programming, or CS 1083 Programming I for Computer Scientists.
Content: Vectors, matrices and tensors; discrete and continuous probability; random variables and expectation; elements of information theory; basic methods for probabilistic learning (maximum likelihood, Bayesian statistics); supervised and unsupervised learning algorithms; neural networks: feedforward, convolutional, recurrent/recursive; loss functions and gradient-based learning; optimization and regularization methods; algorithm implementations; testing on real-world datasets.
