Welcome to CSE 242!

This course has been often been over-subscribed, and enrollment priority is given to CS/CE graduate students, and PhD students in the School of Engineering.  Others will need a permission code to enroll, I will consider giving permission codes the first week of the quarter after the incoming CS grads have all had a chance to enroll.  The course is now heavily subscribed, and I will be reluctant to grant additional permission codes. 

The required textbook is Bishop's Pattern Recognition and Machine LearningHere is the syllabus with office number fixed.

Unfortunately the registrar has scheduled our final towards the end of finals week, on Thursday Dec. 12 from 8-11am.  All students must plan on taking the final exam then, no earlier option will be available.

The expected background for the class includes: 

Algorithms and data structure familiarity level  (sorting, search trees, hashing, etc)

Basic statistics and probability (distributions, random variables, independence, conditional probabilities and distributions, Bayes' Rule)

Linear Algebra

Programming expertise in at least one programming language.  Many students find Python and its SciKit-learn package particularly helpful, although some coming from a statistics  background use R.

Useful on-line resources include Andrew Ng's lecture notes from Stanford , and Ian Goodfellow's deep learning book.

 

AttachmentSize
PDF icon syllabus2019.pdf78.74 KB