Adaptive Systems Spring Term 2010: Course handout.

    Organisers: Inman Harvey and Xabier Barandiaran

    LECTURES:

      Monday 11:00 - 13:00  in ARUNDEL-401

    OBJECTIVE

    To gain some familiarity with a number of different  approaches to modelling and understanding adaptive processes in natural and artificial systems. In particular, to gain some understanding of approaches  to generating adaptive behaviours in autonomous  robots.
     

    PREREQUISITES

    Ability to program, familiarity with a high level procedural language. First term of EASy or IS MSc or completion of 2nd yr. non symbolic AI course.
     

    RATIONALE

    This course will cover recent work in AI, AL and Computational Biology which is geared towards understanding intelligence, both  in  natural  and  artificial  systems,  in  terms  of  the generation of  adaptive  behaviour  in autonomous  agents  acting  in  dynamic uncertain environments. Adaptation  will be studied at both the  evolutionary and the lifetime scale.

    Lectures will give a general coverage of the area. Seminars and exercises will guide students deeper into certain topics. Students are expected to engage in background reading and follow-up references and techniques mentioned in the lectures.
     

    READING LIST

    There are no set texts as such. Some reading material in the form of papers will be provided. Students will find the following useful (most available in the library, bold for the best texts).

    •  Staddon, J.E.R. (2003) Adaptive behavior and learning. (Available Online)

    Cybernetics and Classics

    • Wiener, N.  Cybernetics. 2nd ed. MIT Press, 1962.
    • Ashby, W. Ross. 1960. Design for a Brain. Chapman and Hall, 1960.
    • Piaget, J. Biology and knowledge. University of Chicago Press.  1971.
    • Holland, J.  Adaptation in natural and artificial systems .2nd ed. MIT press, 1992.
    • Langton, C. Artificial Life: An Overview. MIT Press, 1997.
    • Forrest, S. Emergent  Computation. MIT Press, 1991.

    Historical and Philosophical

    • Clark, A. Being There. MIT Press, 1998.
    • Dupuy, J. The Mechanization of Mind. Princeton University Press, 2000.
    • Husbands, P., Holland O., and Wheeler, M. (Eds), The Mechanical Mind in History, MIT Press, 2008.
    • Godfrey-Smith, P.G. Complexity and the Function of Mind in Nature. MIT Press, 1996.

    Autopoiesis and Autonomy

    • Maturana, H. R., & Varela, F. J. (1980). Autopoiesis and cognition. Springer.
    • Varela, F. J. (1979). Principles of Biological Autonomy. Prentice Hall.
    • Barandiaran, X. & Ruiz-­Miraz, K.(.Eds). (2008) Modelling autonomy. Special Issue BioSystems Journal 91(2).

    Robotics

    • Braitenberg, V. Vehicles: Experiments in Synthetic Psychology. MIT Press, 1986.
    • Pfeifer, R. and Scheier, C.  Understanding Intelligence, MIT Press, 1999.
    • Arkin, R.  Behaviour Based Robotics, MIT Press, 1998.
    • Brooks, R. Cambrian Intelligence: The early history of the new AI, MIT Press, 1999. 
    • Husbands, P. and Meyer, J-A..  Evolutionary Robotics, Springer-Verlag, LNCS 1468, 1998.
    • Nolfi, S. and Floreano, S.  Evolutionary Robotics, MIT Press, 2000.
    • Maes, P. Designing Autonomous Agents. MIT Press, 1990.
    • Thrun, S., Burgard, W. and Fox, D.  Probabilistic Robotics. MIT Press, 2005.

    Mathematical Support

    • Abraham, R. and Shaw, C. 1992.  Dynamics: The Geometry of Behavior. Addison-Wesley, 1992.
    • Mareels, I., & Polderman, J. W. (1996). Adaptive systems. Birkhäuser.

    Neuroscience

    • Arbib, M. 1989. The Metaphorical Brain 2. Wiley, 1989.
    • Damasio, A. R. (1994). Descartes' error. G.P. Putnam.
    • Dayan, P. and Abbott, L. Theoretical Neuroscience. MIT Press, 2001.

    Genetic Algorithms and Evolutionary Computation

    • Mitchell, M.  An introduction to genetic algorithms MIT Press, 1996.
    • Back, T. et al Handbook of Evolutionary Computing, OUP/Inst. of Physics, 1997.
    • Goldberg, D. Genetic Algorithms, Addison-Wesley, 1989. 

    Evolution and Biology

    • Lewontin, R. The Triple Helix: Gene, Organism and Environment. HUP, 2000.
    • Maynard Smith, J.   Evolution and the theory of games. CUP, 1982.
    • Gerhart, J. (1997). Cells, Embryos and Evolution. John Wiley & Sons, Limited. 
    • Jablonka, E., & Lamb, M. J. (2005). Evolution in four dimensions. MIT Press.
    • Fusco, G., & Minelli, A. (2008). Evolving pathways. Cambridge University Press.
    • Oyama, S. (2000). The ontogeny of information. Duke University Press.

    Conference Proceedings:

    • SABxx: From Animals to Animats: Proceedings of the International Conference on the Simulation of Adaptive Behavior (1990-)
    • ALIFExx: Artificial Life: Proceedings of the International Conference on Artificial Life (1987-)
    • ECALxx: European Conference on Artificial Life (1989-)

    Journals:

    Adaptive Behavior, Artificial Life,  Evolutionary Computation, Cognitive Neurodynamics, Cognitive Computation, Phenomenology and the Cognitive Sciences, and increasingly many others as well.

    See also the wide range of publications available from the CCNR site.

    A number of web resources, including online reading material and details about assessment.
     

    LECTURE SCHEDULE (TENTATIVE)

    The lectures listed below will not necessarily take exactly one fifty minute period each. Copies of lecture slides will be made available online. This list is tentative.

    Lecture schedule still in preparation.
     

    ASSESSMENT

    N.B. Assessment modes depend on whether you are taking this course as an undergraduate or a postgraduate.
     

    Undergraduates

    Course assessment is split into two parts, with the weights indicated.

    Exercise 1 (50%).
    Programming exercise. You will be given a choice between a GA project and a robot programming project. A 2,000 word program report is to be handed into School office by 4.00 pm on Thursday, week 1 of Summer Term.

    Exercise 2 (50%).
    2,000 word essay on a relevant subject of your choice based on the seminars (to be agreed with Inman Harvey  and/or Xabier Barandiaran by end  of week 8 -- suggested titles will be made available). To be handed in to  School Office by 4.00 pm on Thursday, week 1 of Summer Term.

    Consult your handbook for penalties for late submissions.  You should plan to complete your exercises early, since last minute machine downtime or overloading will not be taken into account. A list of suitable essay topics and programming exercise will be made available. It is advised that you seek feedback on your choice by week 7 by presenting a short proposal for each exercises.
     

    Postgraduates
     

    You will be assessed by a  3,500 word term paper (100%) based on a programming or robotic project (and containing essay elements as well) to be handed into School office by 12.00 pm on first day of Summer term. Suitable topics for programming projects will be made available, but it is expected and advised that you should be able to extend on them and come up with your own ideas. It is advised that you present a short proposal by week 7.

    Refer to Handbook for Candidates for MSc degrees for regulations on late submissions.
     

    SEMINARS/LAB CLASS

    There will be three seminars and a  lab. class during  the course. The  class will be split into groups for these. Seminars will take place in weeks 3, 4, 5 and 6 only. The lab. class will take place in week 7 for PGs. You will be notified of any changes.
     

    Reading material will be made available, watch out for future announcements.