All lecture slides are available in Download section. Thanks everyone for attending the course.

Dates of the Short Course: March 29,30,31   2016


Machine learning plays an important role in modern Image Analysis and Computer Vision research. Problems varied from image segmentation, image registration, image-guided therapy to structure-from-motion, object recognition and scene understanding use machine learning techniques to infer information from visual data. Large variations and complexity of these problems prohibit the possibility of deriving analytic solutions. Therefore, these tasks require “learning from examples” for accurate representation of data and prior knowledge. 

The main aim of this short course is to help advance the scientific research efforts within the broad field of machine learning in image analysis. In particular, the lectures of the first two days are designed to provide the audience an intuitive understanding of the optimization methods behind some common Machine Learning approaches. On the third day, you will get your hands dirty by studying real world problems. A few Computer Vision and Image Analysis papers where Machine Learning is heavily utilized will be critically evaluated (merits, demerits etc.) during this lecture. 

The lectures are mainly focused towards advanced graduate students and researchers who are planning to or using Machine Learning as an Image Analysis tool. The objectives of this short course are 1) to provide an intuitive understanding to recognize the image analysis problems where Machine Learning can be used and 2) the ability to make an informed choice of one Machine Learning Technique over another in your application scenario. 


Topics to be covered: 

1. Introduction

2. Optimization intuitions for Supervised Learning Algorithms

2(a). Discriminative Model (Support Vector Machine)

2(b). Generative Model (Expectation Maximization) 

3. Real Medical Imaging and Computer Vision Application Papers


Schedule & Location: 

Dates: March 29,30,31 2016

Time: 10:00 am - 12:00 pm

Venue: ZIB Lecture Room


Dr. Anirban Mukhopadhyay

mukhopadhyay at