Artificial Cognitive Systems2013HT
No of Lectures
The course will comprise ten two-hour lectures, given over 5 full days.
PhD students in cognitive science (and related research areas, e.g. AI, HCI).
The course was last given
The course has not been given before.
The aim of the course is to provide student with a comprehensive overview of the issues involved in creating an artificial cognitive system, i.e. an autonomous system that can perceive its environment, learns from experience, anticipate the outcome of events, act to pursue goals, and adapt to changing circumstances. It will provide students with a clear understanding of the scope of the domain, the various approaches that exist, and the principal research issues confronting the area.
The course will be given over a period of ten weeks, starting September 23rd, with one full day in Skövde every two weeks. Each day will comprise two two-hour classes, one in the morning and one in the afternoon. Each class will be followed by two hours of self-study and each lecture will begin with a brief review of the material covered in the previous class.
- Overview of the course
- Motivation for studying cognitive systems
- Definition of a cognitive system
Paradigms of Cognitive Science
- History of cognitive science and artificial intelligence
- Cognitivist models of cognition
o Cognitivism and artificial intelligence
o Examples cognitivist systems
- Emergent approaches to cognition
o Connectionist systems
o Enactive systems
- Hybrid approaches
- The function and characteristics of a cognitive architecture
o The cognitivist and emergent perspectives on cognitive architectures
o Desirable characteristics of a cognitive architecture
o Facets of a cognitive architecture: component functionality, component interconnectivity interconnectivity, and system dynamics
- A survey of cognitive architectures
- Requirements for a developmental cognitive architecture
- A case study: the iCub cognitive architecture
- The importance of embodiment for cognition
- Different types of embodiment
Development and Learning
- The relationship between learning and development
- Phylogeny and ontogeny
o The phylogeny/ontogeny trade-off: precocial and altricial species
o Phylogeny: innate capabilities
o Ontogeny: modes of learning, and the importance of motivation & exploration
- Types of autonomy
- Robotic autonomy
- Biological autonomy
- Autonomic systems
- Different scales of autonomy
- Measures of autonomy
- Autonomy and cognition
Course notes will be provided. The following supplementary material will be
1. Bickhard, M. H. Autonomy, function, and representation. Artificial Intelligence, Special Issue on Communication and Cognition, 17(3-4):111–131 (2000).
2. Camazine, S. (2006). Self-organizing systems. In Encyclopedia of Cognitive Science. Wiley.
3. Duch, W, Oentaryo, R. J., and Pasquier, M. Cognitive Architectures: Where do we go from here?, Proc. Conf. Artificial General Intelligence, 122-136 (2008).
4. Froese, T., Virgo, N., and Izquierdo, E. Autonomy: a review and a reappraisal. In e Costa et al., F. A., editor, Proceedings of the 9th European Conference on Artificial Life: Advances in Artificial Life, volume 4648, pages 455–465. Springer (2007).
5. Langley, P.: Cognitive architectures and general intelligent systems. AI Magazine 27(2), 33–44 (2006).
6. Langley, P., Laird, J.E., Rogers, S.: Cognitive architectures: Research issues and challenges. Cognitive Systems Research 10(2), 141–160 (2009).
7. Merrick, K. E. A Comparative Study of Value Systems for Self-motivated Exploration and Learning by Robots, IEEE Transactions on Autonomous Mental Development, Vol. 2, No. 2, 119–131 (2010).
8. Sun, R.: The importance of cognitive architectures: an analysis based on clarion. Journal of Experimental & Theoretical Artificial Intelligence 19(2), 159–193 (2007).
9. Sun, R.: Desiderata for cognitive architectures. Philosophical Psychology 17(3), 341–373 (2004).
10. Sterling, P. Principles of allostasis. In Schulkin, J., editor, Allostasis, Homeostasis, and the Costs of Adaptation. Cambridge University Press., Cambridge, England (2004).
11. Vernon, D. Cognitive system. In Ikeuchi, K., editor, Encyclopedia of Computer Vision. Springer. In Press.
12. Vernon, D. “Cognitive Vision: The Case for Embodied Perception”, Image and Vision Computing, Special Issue on Cognitive Vision, Vol. 26, No. 1, pp. 127-141 (2008).
13. Vernon, D. Enaction as a conceptual framework for development in cog- nitive robotics. Paladyn Journal of Behavioral Robotics, 1(2):89–98 (2010).
14. Vernon, D. and Furlong, D. Philosophical foundations of enactive AI. In Lungarella, M., Iida, F., Bongard, J. C., and Pfeifer, R., editors, 50 Years of AI, volume LNAI 4850, pages 53n ̃–62. Springer, Heidelberg (2007).
15. Vernon, D., Metta. G., and Sandini, G. “A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents”, IEEE Transactions on Evolutionary Computation, special issue on Autonomous Mental Development, Vol. 11, No. 2, pp. 151-180 (2007).
16. Vernon, D., von Hofsten, C., and Fadiga, L. A Roadmap for Cognitive Development in Humanoid Robots, Cognitive Systems Monographs (COSMOS), Springer, ISBN 978-3-642-16903-8 (2010); Chapters 5, 6, 7, and Appendix A.
17. Vernon, D. “Reconciling Autonomy with Utility: A Roadmap and Architecture for Cognitive Development", Proc. Int. Conf. on Biologically-Inspired Cognitive Architectures 2011, A. V. Samsonovich and K. R. Johannsdottir (Eds.), IOS Press, 412-418 (2011).
18. Ziemke, T. What’s that thing called embodiment? In Alterman, R. and Kirsh, D., editors, Proceedings of the 25th Annual Conference of the Cognitive Science Society, Lund University Cognitive Studies, pages 1134–1139, Mahwah, NJ. Lawrence Erlbaum (2003).
19. Ziemke, T. On the role of emotion in biological and robotic autonomy. BioSystems, 91:401—408 (2008).
20. Ziemke, T. and Lowe, R. On the role of emotion in embodied cognitive architectures: From organisms to robots. Cognition and Computation, 1:104–117 (2009).
David Vernon, Skövde Univeristy
David Vernon, Skövde Univeristy
To be decided: it will be either a written examination or a multiple-choice examination. All material in the course notes will be examinable.
Page responsible: Director of Graduate Studies
Last updated: 2012-05-03