263-0008-00L  Computational Intelligence Lab

Semester Spring Semester 2015
Lecturers T. Hofmann
Periodicity yearly course
Language of instruction English
Comment Office hour always on Mondays from 11-12 in room CAB H53


Abstract This laboratory course teaches fundamental concepts in computational science and machine learning based on matrix factorization. This method provides a powerful framework of numerical linear algebra that encompasses many important techniques, such as dimension reduction, clustering, combinatorial optimization and sparse coding.
Objective Students acquire the fundamental theoretical concepts related to a class of problems that can be solved by matrix factorization. Furthermore, they successfully develop solutions to application problems by following the paradigm of modeling - algorithm development - implementation - experimental validation.

This lab course has a strong focus on practical assignments. Students work in groups of two to three people, to develop solutions to three application problems:
1. Compression: Exploiting image statistics to compress an image with minimal perceptual loss.
2. Collaborative filtering: predicting a user interest, based on his own and other peoples ratings. The "Netflix prize" is one such example.
3. Inpainting: Filling in lost parts of an image based on its surroundings.

For each of these problems, students submit their solutions to an online evaluation and ranking system, and get feedback in terms of numerical accuracy and computational speed. In the final part of the course, students combine and extend one of their previous promising solutions, and write up their findings in an extended abstract in the style of a conference paper.