[Eecs_phd] Fall 2017-18 CS 4900 / 5900 Machine Learning

[Hunter, Tiffany]

Machine Learning course in the Fall, for undergraduate (CS 4900,
elective) and graduate students (CS 5900).

Title:
====
   Machine Learning

Time:
====
   Tue & Thu 10:30am -- 11:50am

Instructor:
========
   Razvan Bunescu
   bunescu at ohio.edu
   http://ace.cs.ohio.edu/~razvan

Course Description:
===============
Machine Learning is about developing algorithms that find patterns in the data in order to enable computers to improve their performance on a given task. This introductory course will cover the fundamental topics of classification, regression and clustering, starting with simple models such as perceptrons, logistic regression, Naive Bayes, and nearest neighbors and, time-permitting, ending with more advanced models such as multi-layer neural networks. The description of the formal properties of the algorithms will be supplemented with practical applications in a wide range of areas including natural language processing, computer vision, biomedical informatics, and music analysis. The fundamental topics covered in this course will also prepare students for taking more advanced courses in data mining and deep learning.

Prerequisites:
===========
Students are expected to be comfortable with programming in Python and familiar with basic concepts in linear algebra and statistics, e.g. a B or better in Math 3200 or Math 3210. Theoretical exercises will also require students to be comfortable with articulating mathematical proofs. Relevant background material in linear algebra, probability theory and statistics will be made available during the course.