6.S093: Visual Recognition through Machine Learning Competition

Instructors:Aditya Khosla, Joseph J. Lim
Sponsored by:
Contact: viscomp@mit.edu
Meeting time:1 - 3pm
Location:56 - 154

Class description

Have you ever wondered how your camera is able to detect faces when you take pictures, or how a Kinect is able to recognize your every move? Take this course to learn more about these topics and build a visual recognition system of your own! Come compete against your friends in a battle of wits, grit and Matlab for a variety of cash prizes provided by our generous sponsors. In this course, we will provide a comprehensive introduction to visual recognition using machine learning.

The course is designed to give you hands-on experience in building your own real-world computer vision system: each lecture will consist of an hour of instruction followed by an hour of lab. For the last few lectures, the focus will be on building your own visual recognition system and the instructors will be available to bounce ideas and help you along the way.

Finally, as this class is meant to be practical, I welcome any suggestions on topics and teaching style that will help you gain more from this course.

Visual Recognition Competition



Week Date Topic Presenter Lecture Notes
1 January 13 Introduction to Computer Vision Aditya
Lecture 1 [ppt] [pdf]
Matlab tutorial [ppt] [pdf] [code]
January 14 Image Representations Joseph
Lecture 2 [ppt] [pdf]
Exercise (Solution)
January 15 Image Representations (continued) Aditya
Lecture 3 [ppt] [pdf]
January 16 Introduction to Machine Learning Joseph
Lecture 4 [ppt] [pdf]
Exercise (Solution)
January 17 Introduction to Deep Learning Aditya
Lecture 5 [ppt] [pdf]
2 January 21 Guest lecture Ce Liu
Microsoft Research
January 22 Competition prep    
January 23 Competition prep    
January 24 Competition prep    
3 January 29 Student presentations + Awards Ceremony You!  


We would like to thank the MIT IEEE/ACM Club for their support in organizing this competition.