Maschinelles Lernen B, WS 2006
Institut für Grundlagen der Informationsverarbeitung (708) last changes:

ML A versus ML B:

Each of these two courses is offered every second year. Their content is independent from each other (see course descriptions on http://www.igi.tugraz.at/maass/lehre.html). Both courses count as core courses for the Computational Intelligence Catalogue, and belong to the course catalogue for Doctoral Students (ML B is not yet listed there, but will be shortly according to Prof. Schmalstieg).

Course Contents:

The current methods for the design of robustly functioning large computing systems are challenged by the need to design larger software systems with very large numbers of interacting components, and also by the need to design hardware devices that carry out computations with very large numbers of somewhat unreliable components on the nanoscale. In addition one needs to develop computing systems (including robots) that can continuously and autonomously learn, i.e., learn without a supervisor which tells them during training at each instance what the ideal action would be. An important task for computer science is to develop tools that will be able to provide this new generation of system design principles and algorithms. Whereas one may doubt whether this task can be solved, nature provides a positive example: Biological organisms consist of extremely large number of communicating components that evolve without a supervisor, and carry out extremely complex computations not only within brains, but also within the gene regulation network of each cell. In addition, biological systems are highly adaptive, i.e., they can learn to cope with changing problems and environments.

The goal of this course is to examine the most promising ideas for the design of autonomously learning and evolving systems, and to introduce the students to software that allows them to ealuate the potential and limitations of these ideas, and to develop better ideas. Whereas the so-called genetic or evolutionary algorithms have dominated research on methods for evolving well-functioning articifial organisms in previous decades (which has lead to some limited success), one has now realized that nature actually uses quite different principles for evolving, improving and maintaining biological organisms than those which were implemented in these algorithms: Since there is no master-agent that supervises the development of biological organisms, nature has invented powerful distributed methods for developing functioning multi-cell organisms, based on gene regulation networks within each cell that follow a complex set of rules (encoded in the DNA) that tell the cell how to respond to external signals (from other cells, or from the environment), and when to build and renew cell components.We will discuss in this course simple mathematical models that capture essential aspects of these design principles, and which provide new methods for the design of robustly functioning, self-repairing, and autonomously learning artificial organisms. In addition we present the main methods of reinforcement learning, which is apparently the primary type of learning that is used by autonomously learning biological organisms.

Covered topics:



News

This page lists all updates of this course homepage. It will be kept up-to-date during the semester.

10.07.08 Welcome
10.08.08 The course ML B will be added to the course catalog for Informatik doctoral students
15.09.08 Information on ML A versus ML B added.
8.10.08 Exercises rescheduled for Tuesday, 15:00 - 16:00.


Assignment cover

Please use for all assignments the following cover.pdf.

Tasks

On this site you find the problem sets and projects for the practicals.

Exercises



Problem Sets

Nr.IssuedSubmission DatePresented onLinkAdditional Material
114.10.200828.10.200828.10.2008Genetic Algorithms ga.zip
214.10.200828.10.200828.10.2008Comparison of Learning Algorithms sa.zip
331.10.20084.11.200811.11.2008Distributed computing: WTA simulator.zip
431.10.20084.11.200811.11.2008Patterning simulator.zip
524.11.20089.12.20089.12.2008Small-world networks
624.11.20089.12.20089.12.2008Robustness robustness.zip
719.12.200813.1.200913.1.2009RL theory I
819.12.200813.1.200913.1.2009RL theory II
919.12.200813.1.200913.1.2009RL game
1019.1.200920.2.2009-On- and off-policy learningexamples.zip
1119.1.200820.2.2009-Function approximationexamples.zip
1219.1.200920.2.2009-Own ideas for learning algorithms


Projects



Please post your questions concerning the problem sets to the MLB Newsgroup, or send them directly to Stefan Häusler.

People Involved

This course is being organized by Institut für Grundlagen der Informationsverarbeitung, Inffeldgasse 16b/1. Stock, A-8010 Graz.

Lecturer / Instructor

Teaching assistant

Office

If you have any questions or problems, please do not hesitate to contact one of the above persons.


Place and Date

Lectures:

Time: Monday, 13:00-15:00
Location: SIEMENS TS Hörsaal (HS i11), Inffeldgasse 16b
First lecture: 13.10.2008


Exercises:

Time: Tuesday, 15:15 - 16:00
Location: Seminarraum, IGI, Inffeldgasse 16b
First lecture: 14.10.2008


Literature


  • Banzhaf et al.: From artificial evolution to computational evolution: a research agenda, Nature (2006) (http://www.cs.mun.ca/~banzhaf/papers/nrg2006.pdf)


  • Course Material

    Literature

  • Lecture notes 1
  • Design and Application of Self Developing Organisms, Master thesis, Roland Unterberger (2008)
  • Theory of Reinforcement Learning, DI Michael Pfeiffer (2006)
  • Lecture notes MLB WS 2006, DI Michael Pfeiffer (2006)
  • Movies

  • Transcription
  • Translation
  • Slides from the lecture

    LectureDateTopicSlides
    20.10.2008 Genetic algorithms in nature Slides (PPT)
    12.1.2009 The most common reinforcement learning algorithms Slides (PPT)
    19.1.2009 Function approximation Slides (PPT)

    Slides from Practicals

    LectureDateTopicSlides
    114.10.2008 Organisation Slides (PDF)
    221.10.2008 Genetic Algorithms and Simulated Annealing Slides (PDF)
    34.11.2008 Introduction to the AO simulator Slides (PDF), XML files
    425.11.2008 Scale-free and small-world networks Slides (PDF)


    SECO Project


    Sources for Scientific Literature


    Artificial Life


    Reinforcement Learning


    Genetic Algorithms