Machine Learning

Advanced Models and Algorithms in Machine Learning

Instructor: J. Lücke
Language: English
Time and place: Thursday 14:00 - 16:00, W30 2-211 (NeSSy)

Prerequisites

Knowledge in higher Mathematics including Analysis and Linear Algebra for Physicists, Mathematicians, Engineers and Computer Scientists. Knowledge in probabilistic data modelling and standard Machine Learning approaches.

Content

In this seminar recent developments of models and algorithms in Machine Learning will be studied. Advances of established modelling approaches and new approaches will be presented and discussed along with the applications of different current algorithms to application domains including: auditory and visual signal enhancements, source separation, auditory and visual object learning and recognition, auditory scene analysis and inpainting. Furthermore, Machine Learning approaches as models for neural data processing will be discussed and related to current questions in Computational Neuroscience.

Schedule of the Machine Learning Seminar Winter Term 2014/2015

Oct-23

Jörg Lücke

Introduction and organization

Oct-30

Maryam Sadreddini, Allan Maheri

Acoustic data representation - log-spectorgrams, cocheagrams, LPC etc.

Nov-13

Jörg Lücke

Non-linear dictionary learning for sensory data - occlusion and masking

Nov-20

Bernd Meyer, Angel Castro et al.

Acoustic data classification

Nov-27

Travis Monk

The origin of inference

Dec-4

Dennis Forster and Saboor Sheikh

Deep learning

Dec-11

Nasser Mohammadiha

Standard and probabilistic NMF versions

Dec-18

Cristiano Micheli

Neural receptive fields, STRFs, acoustic features and their neural correlates

Jan-8

Joachim Thiemann / Steven van de Par (4.15pm, note changed time for this talk!!)

The Oldenburg acoustics group system for speech processing

Jan-15

Georgios Exarchakis and Jörg Lücke

Standard and new sparse coding algorithms

Outcome

The students will learn about recent developments and state-of-the-art approaches in Machine Learning, and their applications to different data domains. By presenting scientific studies in the context of currently used models and their applications, they will learn to understand and communicate recent scientific results. The presentations will use computers and projectors. Programming examples and animations will be used to support the interactive component of the presentations. In scientific discussions of the presented and related work, the students will obtain knowledge about current limitations of Machine Learning approaches both on the theoretical side and on the side of their technical and practical realizations. Presentations of interdisciplinary research will enable the students to carry over their Machine Learning knowledge to address questions in other scientific domains.

Literature

  • Pattern Recognition and Machine Learning, C. M. Bishop, Springer 2006.
  • Information Theory, Inference, and Learning Algorithms, D. MacKay, Cambridge University Press, 2003. (online available)
  • Machine Learning: A Probabilistic Perspective, K. P. Murphy, MIT Press, 2012.
  • Standard Journals of the field.