[ICS 435] Machine Learning Fundamentals
||First HW given. (Perceptron)
||Remarks on presenting
||First HW due.
||Supervised learning I: Generalization Error vs. training error. Introduction to statistical learning theory and support vector machines (SVM)|
||Support vector learning: Support
(SVM) and Support vector regression (SVR).
||Second HW given.
||Introduction to regression
and Bayesian Inference.
||Extra credit HW
||Guest lecture: Prasad
Santhanam on linear regression.
learning II: Introduction to artificial neural networks and
||Guest tutorial: Giacomo
Indiveri on Neuromorphic engineering.
||Introduction to unsupervised
||Third HW given. (k-means)|
to the use of information theory in unsupervised learning.
||From thermodynamics to information theory to machine learning.|
||Behavioral learning (pending student interest and time frame). OR work on Final Project||Third HW due. EC HW due.
||Work on Final Project.|
||Final Project Presentations.||Final Project due.
||Study period. Last day of
instruction is 12/7. Final taken online the following week.