Proseminar: Machine Learning Methods for Text, Audio and Video Analysis
QAC 239
Spring 2019
| Section:
01
|
| This course may be repeated for credit. |
| Crosslisting:
CIS 239 |
| Certificates: Applied Data Science |
In this course, students will learn machine learning techniques to analyze text, audio, and video data. The course consists of three parts: text analysis, audio analysis and video analysis. Each part will first introduces how these non-traditional data can be converted into mathematical objects suitable for computer processing and, particularly, for the application of machine learning techniques. Then students will learn a selection of supervised and unsupervised learning algorithms that are effective for text, audio, image/video analysis. Finally, students will explore major applications of these techniques such as sentiment analysis, speech emotion recognition, face recognition, pedestrian detection, keyframe extraction. |
|
| Credit: 1 |
Gen Ed Area Dept:
NSM QAC |
| Course Format: Laboratory | Grading Mode: Graded |
| Level: UGRD |
Prerequisites: COMP112 OR QAC155 OR QAC156 |
|
Fulfills a Requirement for: (CADS)(DATA-MN)(PSYC) |
|
Past Enrollment Probability: 75% - 89% |
| SECTION 01 | | Special Attributes: CQC |
Major Readings: Wesleyan RJ Julia Bookstore
Sample readings:
An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, Springer, 2013.
Free e-book available online at: http://www-bcf.usc.edu/~gareth/ISL/ISLR%20Sixth%20Printing.pdf
Introduction to Audio Analysis: A MATLAB Approach by Theodoros Giannakopoulos and Aggelos Pikrakis, Academic Press, 2014.
Computer Vision with OpenCV and Python 3: Practical examples workbook by Thileepan Stalin and Divya Vetriselvan, Amazon Digital Services LLC, 2017.
Additional weekly reading materials will be provided through Moodle.
|
Additional Requirements and/or Comments:
The course requires a basic programming background and that is why COMP 112, QAC155, QAC156 etc. are formal prerequisites. In addition students are expected to have at least an introductory course in data analysis. Pre-req overrides will be approved by the Professor for students who satisfy this basic requirement through other course work. The course includes a strong lab component and programming in Python is a significant part of the course work.
Professor Kaparakis will attend to Pre-req override requests during pre-registration, but will not be the instructor for this course. |
| Instructor(s): Yao,Jielu Times: ..T.R.. 01:20PM-02:40PM; Location: ALLB204; |
| Total Enrollment Limit: 16 | | SR major: 0 | JR major: 0 | | |
| Seats Available: 1 | GRAD: X | SR non-major: 7 | JR non-major: 7 | SO: 2 | FR: 0 |
| Drop/Add Enrollment Requests | | | | | |
| Total Submitted Requests: 3 | 1st Ranked: 0 | 2nd Ranked: 0 | 3rd Ranked: 1 | 4th Ranked: 0 | Unranked: 2 |
|
|