Department of Computer Science

Dr. Daniel Polani

Reader in Artificial Life

Overview

• Research
• Publication List
• The Adaptive Systems Research Group
• Workshops, Symposia and Conferences
  • Machine Learning Approaches to Statistical Dependences and Causality (Dagstuhl Seminar)
  • Second International Workshop on Guided Self-Organization, 2009, Max-Planck Institute for Mathematics in the Sciences, Leipzig
  • Principled Theoretical Frameworks for the Perception-Action Cycle, Mini-Symposium and Workshop at NIPS 2008
  • International Workshop on Guided Self-Organization, 2008, CSIRO, Sydney
• Teaching
• Multiagent Projects and Software
  • RoboCup: our robotic soccer activities
    1. visit also our team page Bold Hearts
    2. and the official RoboCup page Team
    3. RoboCup 2006 Press Snippets
  • XRaptor, a multiagent simulation system with tournament support, particularly useful for teaching, in particular in conjunction with the new XGrabtor frontend.
  • DMarks II: a trading agent scenario simulation
• Are you interested in a student project?

Research

• Artificial Intelligence: can we imitate the processes that allow animals and humans to take flexible decisions in a complex and difficult environment? Being able to adapt themselves to different conditions gracefully? Being able to absorb changes in the environmental conditions? Can we do so incorporating learning ability, without compromising generalization ability, without hand-coding all necessary rules into a system? Are there general principles underlying intelligent information processing in living beings which we can exploit without having to resort to specialized solutions that vary from task to task?

• Artificial Life: this question is closely related to Artificial Intelligence. What makes living systems live? What are the mechanisms that allow complexity arise in nature? What role play emergent and self-organizing mechanisms in this context and can this role be formalized? Can understanding of mechanisms for "life" teach us something about how to achieve intelligence in artificial systems?

• Information Theory for Intelligent Information Processing: To put it saucily: information theory is something like the logarithm of probability theory. In early modern times the logarithm simplified multiplication into addition which was more accessible to calculation. Today, information theory transforms many quantities of probability theory into quantities which allow simpler bookkeeping.

  More seriously, information theory is one of the most universal concepts with applications in computer science, mathematics, physics, biology, chemistry and other fields. It allows a lucid and transparent analysis of many systems and provides a framework to study and compare seemingly different systems using the same language and notions. Recent research in learning models, e.g. Neural Networks, emphasizes the universal role of information. Can information theory open a universal approach towards the development of Artificial Intelligence and the studies of Artificial Life?

  Here is a question I was asking myself (or, actually Usenet, to be precise) a couple of years ago about Information Theory and Stochastic Control.

  There was no reply from Usenet, however, a few results relevant to that question have come up (or we have become aware of) in the meantime:

  • The Information Bottleneck Principle by Tishby et al.
  • An information-theoretic approach to the study of control systems and Information-theoretic limits of control by Touchette and Lloyd and its classical predecessor Law of Requisite Variety by Ashby (1956)
  • Measures for representations in evolved agents by Avraham, Chechik, Ruppin (ECAL 2003)
  • Information Theory for Cognitive Systems by Ay
  • The Emergence and Complexity website complex with interesting discussions by Shalizi (including material from the Crutchfield and Santa Fe school)
  • The work relating information theory and sensory coding by Nadal and Parga
  • Work regarding decorrelation by Barlow (H. B. Barlow, "Possible principles underlying the transformation of sensory messages," Sensory Communication, pp. 217--234, 1961), Attneave or Atick (Atick, JJ, & Redlich, AN (1990) Towards a theory of early visual processing. Neural Computation 2, 308-320)
  • The Fitness Value of Information by Bergstrom and Lachmann
  • Mapping Information Flow in Sensorimotor Networks (PLoS Computational Biology, Oct 2006, DOI: 10.1371/journal.pcbi.0020144) by Lungarella and Sporns, also featured in New Scientist. There is quite some other work in that direction by Sporns and Lungarella
  • The Role of Information and Statistics in Early Visual Coding by Li Zhaoping
  • Infotaxis as a search strategy (plus a number of other interesting systematic approaches to modeling biological systems) by Shraiman and collaborators.
  • NIPS 2007 Workshop on: Hierarchical Organization of Behavior organized by Yael Niv, Matthew Botvinick and Andrew Barto; although not strictly information-theoretical, many of the issues discussed in the papers listed on this site are closely related to the issues we are interested in or have an information-theoretic counterpart. This website includes links to highly relevant papers by the organizers as well as by Kaelbling, Schmidhuber, Wiering and others.
  • An Information-Theoretic Approach for the Quantification of Relevance by Polani et al. and the newer paper about Relevant Information in Optimized Persistence vs. Progeny Strategies (the latter is a significantly more elaborate and mature treatment of the matter, but deals with a whole complex of problems at one fell swoop which makes it harder to read)
  • Organization of the Information Flow in the Perception-Action Loop of Evolved Agents (see also this website and our other publication websites) by Klyubin et al.
  • Information Self-Structuring for Developmental Robotics by Olsson et al. (see also e.g. this website).

  We will occasionally update this list when we a paper that seems particularly close to addressing above question or a question related to it.

  Some further useful links to resources (people/papers) on Biology and Information can be found at the

  • IEEE Information Theory Society

• Sensor Evolution: Speaking of information, living beings and artificial agents survive by obtaining information from the environment. Due to the physical limitations of the agents, not all environmental information is gathered; the sensors will concentrate on relevant information that is essential for the goal of the agent.

  How is this selection process attained in nature? How can we copy it in artificial systems? How are new channels of environmental information be tapped and exploited by a system that originally accessed a different set of information channels? Can we make use of it in artefacts?

• Collective and multiagent systems: Among the most complex systems are systems of multiple coacting and coevolving agents. These systems are, in general, very difficult to describe and to design properly. Such systems provide a natural high-complexity environment for studies on artificial intelligence and artificial life and are ideal testbeds for theories about social interaction.

  Successful multiagent studies have been carried out e.g. in the framework of

  • the XRaptor multiagent simulator and
  • the RoboCup project (see e.g. the official page, or Bold Hearts, the University of Hertfordshire RoboCup team)
  • DMarks II: an agent-based trade scenario simulation

Publication List

The Adaptive Systems Research Group

• 2008-2009 (current preliminary)

Students

Malte Harder	Self-Organization
Sander van Dijk	Robot Learning
Christoph Salge	Informational models of Social Systems
Tom Anthony	Empowerment and its Dynamics
Philippe Capdepuy	Perception-Action Loop/Homeostasis
Dorothee Francois	Human-Robot Interaction, PhD awarded February 2009
Tobias Jung	Fast Reinforcement Learning with Kernel Machines; remote supervision, PhD awarded February 2008
Alexander Klyubin	Organization of Information Flow through the Perception-Action Loop, PhD awarded May 2007
Robert Lowe	Multiagent Systems/Evolution of Expression, PhD awarded February 2007
Lars Olsson	Information Self-Structuring for Developmental Robotics, PhD awarded June 2006

Visiting Researchers/Alumni

• Jan T. Kim (UEA)
• Tobias Jung(U Texas at Austin)
• Marco Möller, University of Darmstadt - see also Young Researchers Association (in German)

Are you interested in a student project?

The Artificial Neural Networks Research Group

Workshops, Symposia and Conferences (Selection)

Coming Events

Past Events

• Artificial Life XI, see also the themed session at Alife XI on Information in Complex Systems and Artificial Life, with some Press Snippets from the BBC
• Invited Session on Evolutionary and Self-Organizing Sensors, Actuators and Processing Hardware at KES 2006
• 50th Anniversary Summit of Artificial Intelligence, Monte Verita, July 2006
• International Conference on Complex Systems
• RoboCup 2006, Bremen
• Artificial Life X
• Tutorial on the Evolution of Sensors and the Perception-Action Loop at ALIFE X
• Understanding Complex Systems 2006
• Ninth Artificial Life Conference - 12-15 Sept 2004, deadline 30 Jan 2004
• The RoboCup 2003 volume is out in August 2004 (Springer)
• 2004 NASA/DoD Conference on Evolvable Hardware June 24-26, 2004 Seattle, Washington, USA
• International Lisp Conference, October 2003, New York
• EPSRC Network Evolvability and Sensor Evolution Symposium, April 2003, Birmingham (UK)
• RoboCup, June 2003, Padova (Italy)
• ECAL 2003, September 2003, Dortmund (conference webcast at Complexity Digest)

Seminars of the "Studienstiftung des deutschen Volkes" (German Merit Foundation)

• Information: Currency of Life at the Summer Academy 2008 at Olang/Italy (on-demand translation)
• Complex Systems and Artificial Life at the Summer Academy 2004 at Ftan/Switzerland (on-demand translation)

Teaching

2009-2010

• Constructive Artificial Intelligence
• Bioinformatics (Programming in Python)

2008-2009

• Theory and Practice of Artificial Intelligence

2007-2008

• Social Intelligence

2005-2006

• Advanced Symbolic AI
• Artificial Intelligence (MCOM0079, Sem B)

Multiagent Projects and Software

• XRaptor: a tournament-based multiagent simulation environment; an ideal tool for multiagent teaching and research;
• XGrabtor: a graphical frontend for XRaptor;
• RoboCup:
  • Official Page
  • Bold Hearts, the University of Hertfordshire RoboCup team;
  • DMarks II: an agent-based trade scenario simulation.
• C++
• Lisp

Travel Directions

Former Addresses

UH and Beyond

• New Scientist: Distribution of UK's Influential Researchers
• Official Staff Website
  (will only be updated sporadically - if you wish up-to-date information, please refer to the current page)

Mottos