Neural Machine Learning I

COMP / ELEC / STAT 502, spring 2024

This web site may be updated at any time for implementation of Covid-19 measures as necessary, corresponding changes may occur relative to the posted Syllabus and other posting at this site. 

If you intend to enroll to this course: If you are an undergraduate you will need my permission. If you are a graduate student you do not need my permission to register, but you may contact me if you are unsure about your preparedness. In both cases, please check the Required Background to assess your eligibility/preparedness and then send me the information I list there so that I can assess your situation.

Class meets: TR 2:30 - 3:45pm, room DCH 1042
This class is based on in-person instruction, subject to changes if Covid-19 measures should require. Classes will not be recorded unless Covid-19 enforces remote instruction.

Instructor: Erzsébet Merényi
Office/Phone: MXF 229, 713-348-3595  email preferred
Office hour: by appointment
Preferred window: Tuesday 4:15 - 5:30pm (preliminary)
Make appointments in this window if possible.
You may also come by in this window unannounced but only an appointment ensures that I am there. You can ask for time outside the preferred window, and I will accommodate your request at my earliest possibility but cannot promise to find time immediately.

Teaching Assistant, grader and contact information:
Ziting Tang TA
Advising by TA: by appointment
Preferred window is TBA
Isita Polamarasetti grader

Sample Course Outline
Required Background
Course Flyer
Disability Allowances
Title IX

Last Updated: April 16, 2024

Welcome to biologically inspired neural information processing!
Short course description: Review of major Artificial Neural Network paradigms. Analytical discussion of supervised and unsupervised learning. Emphasis on state-of-the-art Hebbian (biologically most plausible) learning paradigms and their relation to information theoretical methods. Applications to data analysis such as pattern recognition, clustering (information discovery), classification, non-linear PCA, independent component analysis, with examples from image and signal processing and other areas. 

2023 Pizza Points