A linear-complexity reparameterisation strategy for the hierarchical bootstrapping of capabilities within perception-action architectures

Image and Vision Computing

Volumn 27, Issue 11, 2009, Pages 1702-1714

  Shevchenko, Mikhail ^a   Windridge, David ^a   Kittler, Josef ^a  

^a UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

Cognitive vision; Machine learning (unsupervised); Optimisation; Perception action architectures; Subsumption architecture

Indexed keywords

ARCHITECTURAL DESIGN; COMPUTER VISION; EDUCATION; MOTORS; ROBOT LEARNING;

COGNITIVE VISION; MACHINE LEARNING (UNSUPERVISED); OPTIMISATION; PERCEPTION-ACTION ARCHITECTURES; SUBSUMPTION ARCHITECTURE;

LEARNING ALGORITHMS;

EID: 68649087605     PISSN: 02628856     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.imavis.2008.12.002     Document Type: Article

References (40)

1. Barto G., and Mahadevan S. Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems 13 (2003) 341-379
2. Borghi A.M., Parisi D., and Di Ferdinando A. Action and hierarchical levels of categories: a connectionist perspective. Cognitive Systems Research 6 (2005) 99-110
3. Brooks R.A. New approaches to robotics. Science 253 (1991) 1227-1232
4. Castellano G., Fanelli A., and Mencar C. A neuro-fuzzy network to generate human-understandable knowledge from data. Cognitive Systems Research 3 (2002) 125-144
5. Chen C.-H., and Honavar V. A neural-network architecture for syntax analysis. IEEE Transactions on Neural Networks 10 1 (1999) 94-114
6. S. Coradeschi, A. Saffiotti, Anchoring symbols to sensor data: preliminary report, in: Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, AAAI Press/The MIT Press, 2000, pp. 129-135.
7. Şahin E., Çakmak M., Doǧar M.R., Uǧur E., and Üçoluk G. To afford or not to afford: a new formalization of affordances toward affordance-based robot control. Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems 15 4 (2007) 447-472
8. Elfwing S., Uchibe E., Doya K., and Christensen H.I. Evolutionary development of hierarchical learning structures. IEEE Transactions on Evolutionary Computation 11 2 (2007) 249-264
9. Fiechter C.N. Efficient reinforcement learning. Computational Learning Theory (1994) 88-97
10. Fodor J., and Pylyshyn Z. Connectionism and cognitive architecture: a critical analysis. Cognition 28 (1988) 3-71
11. Gibson J.J. The Ecological Approach to Visual Perception (1979), Houghton-Mifflin, Boston
12. Giles L., and Omlin C.W. Extraction, insertion and refinement of symbolic rules in dynamically driven recurrent neural networks. Connection Science 5 (1993) 307-337
13. Kraetzschmar G.K., Sablatnoeg S., Enderle S., and Palm G. Application of neurosymbolic integration for environment modelling in mobile robots. Hybrid Neural Systems (2000)
14. G. Granlund, Organization of architectures for cognitive vision systems, in: Proceedings of Workshop on Cognitive Vision, Schloss Dagstuhl, Germany, October 2003.
15. Harnad S. The symbol grounding problem. Physica D 42 (1990) 335-346
16. Harnad S. Categorical Perception. Encyclopedia of Cognitive Science (2003), Nature Publishing Group, Macmillan
17. A. Hirose, Self-organizingly emerging activeness architecture realized by coherent neural networks, in: Ninth International Conference on Artificial Neural Networks ICANN 99, vol. 2, 1999, pp. 726-731.
18. Jonker C., Treur J., and Wijngaards W. A temporal modelling environment for internally grounded beliefs. Cognitive Systems Research 4 3 (2003) 191-210
19. L. P. Kaelbling, Hierarchical learning in stochastic domains: preliminary results, in: International Conference on Machine Learning, 1993, pp. 167-173.
20. Kuipers B., Beeson P., Modayil J., and Provost J. Bootstrap learning of foundational representations. Connection Science 18 2 (2006)
21. MacDorman K. Grounding symbols through sensorimotor integration. Journal of the Robotics Society of Japan 17 (1999) 20-24
22. Markman A., and Dietrich E. Extending the classical view of representation. Trends in Cognitive Sciences 4 (1991) 470-475
23. Newell A. The knowledge level. Artificial Intelligence 18 (1982) 87-127
24. Pfeifer R. Cognition - perspectives from autonomous agents. Robotics and Autonomous Systems 15 1-2 (1995) 47-70
25. R. Pozarlik, Integrating parallel computations and sequential symbol processing in neural networks, in: Proceedings of the IEEE World Congress on Computational Intelligence, IEEE Press, Piscataway, NJ, 1998, pp. 1444-1449.
26. Schalkoff R.J. Artificial Intelligence: An Engineering Approach (1990), McGraw-Hill, New York, USA
27. Scherl R.B., and Levesque H.J. Knowledge action and the frame problem. Artificial Intelligence 144 1-2 (2003) 1-39
28. Sharkey N., and Ziemke T. Mechanistic vs. phenomenal embodiment: can robot embodiment lead to Strong AI?. Cognitive Systems Research 2 4 (2001) 251-262
29. Spall J.C. Introduction to Stochastic Search and Optimization (2003), John Wiley & Sons, Inc., New York, NY, USA
30. M. Steedman, Formalizing affordance, in: 24th Annual Meeting of the Cognitive Science Society, Fairfax, VA, 2002, pp. 834-839.
31. Steels L. When are robots intelligent autonomous agents. Robotics and Autonomous Systems 15 1-2 (1995) 3-10
32. L. Steels, The origins of syntax in visually grounded robotic agents, in: M. Pollack (Ed.), Proceedings of the 10th International Joint Conference on Artificial Intelligence, Nagoya, AAAI Press, Menlo-Park, CA, 1997, pp. 1632-1641.
33. A. Stoytchev, Toward learning the binding affordances of objects: a behavior-grounded approach, in: Proceedings of AAAI Symposium on Developmental Robotics, Stanford University, March 21-23, 2005, pp. 17-22.
34. Sun R. Symbol grounding: a new look at an old idea. Philosophical Psychology 13 (2000) 149-172
35. Sun R., Merrill E., and Peterson T. From implicit skills to explicit knowledge: a bottom-up model of skill learning. Cognitive Science 25 2 (2001) 203-244
36. S. Tano, D. Futamura, Y. Uemura, Efficient learning by symbol emergence in multilayer network and agent collaboration, in: The Ninth IEEE International Conference on Fuzzy Systems, 2000, pp. 1056-1061.
37. A. Ueno, H. Takeda, T. Nishida, Learning of the way of abstraction in real robots, in: 1999 IEEE International Conference on Systems, Man, and Cybernetics, vol. 2, 1999, pp. 746-751.
38. Wermter S. Knowledge extraction from transducer neural networks. Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks and Complex Problem-Solving Techniques 12 (2000) 27-42
39. Windridge D., and Kittler J. Epistemic constraints on autonomous symbolic representation in natural and artificial agents. In: Smolinski T.G., Milanova M.G., and Hassanien A.-E. (Eds). Applications of Computational Intelligence in Biology: Current Trends and Open Problems, Studies in Computational Intelligence (SCI) vol. 122 (2008), Springer
40. T. Ziemke, Towards autonomous robot control via self-adapting recurrent networks, in: Sixth International Conference on Artificial Neural Networks ICANN 96, 1996, pp. 611-616.