Self-organizing neural networks integrating domain knowledge and reinforcement learning

IEEE Transactions on Neural Networks and Learning Systems

Volumn 26, Issue 5, 2015, Pages 889-902

  Teng, Teck Hou ^a   Tan, Ah Hwee ^a   Zurada, Jacek M ^b,c  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^b UNIVERSITY OF LOUISVILLE   (United States)

^c UNIVERSITY OF SOCIAL SCIENCES   (Poland)

Author keywords

Adaptive resonance theory (ART); domain knowledge; reinforcement learning (RL); self organizing neural networks.

Indexed keywords

COMPLEX NETWORKS; LEARNING SYSTEMS; NEURAL NETWORKS; REAL TIME SYSTEMS;

ADAPTIVE RESONANCE THEORY; DOMAIN KNOWLEDGE; KNOWLEDGE STRUCTURES; LEARNING EFFICIENCY; MODEL COMPLEXITY; NAVIGATION PROBLEM; PURSUIT EVASION; SELF-ORGANIZING NEURAL NETWORK;

REINFORCEMENT LEARNING;

ALGORITHM; ARTIFICIAL NEURAL NETWORK; AUTOMATED PATTERN RECOGNITION; COGNITION; COMPUTER SIMULATION; HUMAN; KNOWLEDGE; REINFORCEMENT; THEORETICAL MODEL;

ALGORITHMS; COGNITION; COMPUTER SIMULATION; HUMANS; KNOWLEDGE; MODELS, THEORETICAL; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED; REINFORCEMENT (PSYCHOLOGY);

EID: 84928007697     PISSN: 2162237X     EISSN: 21622388     Source Type: Journal    
DOI: 10.1109/TNNLS.2014.2327636     Document Type: Article

References (32)

1. A. M. Shapiro, "How including prior knowledge as a subject variable may change outcomes of learning research," Amer. Educ. Res. J., vol. 40, no. 1, pp. 159-189, 2004.
2. A.-H. Tan, "Cascade ARTMAP: Integrating neural computation and symbolic knowledge processing," IEEE Trans. Neural Netw., vol. 8, no. 2, pp. 237-250, Mar. 1997.
3. Y. S. Abu-Mostafa, "Learning from hints in neural networks," J. Complex., vol. 6, no. 2, pp. 192-198, 1990.
4. M. Pazzani and D. Kibler, "The utility of knowledge in inductive learning," Mach. Learn., vol. 9, no. 1, pp. 57-94, 1992.
5. T. M. Mitchell and S. Thrun, "Explanation-based neural network learning for robot control," in Advances in Neural Information Processing Systems 5. San Mateo, CA, USA: Morgan Kaufmann, 1993, pp. 287-294.
6. G. G. Towell and J. W. Shavlik, "Interpretation of artificial neural networks: Mapping knowledge-based neural networks into rules," in Advances in Neural Information Processing Systems 4. San Mateo, CA, USA: Morgan Kaufmann, 1992, pp. 977-984.
7. L.-M. Fu, "Knowledge-based connectionism for revising domain theories," IEEE Trans. Syst., Man, Cybern., vol. 23, no. 1, pp. 173-182, Jan./Feb. 1993.
8. C. H. C. Ribeiro, "Embedding a priori knowledge in reinforcement learning," J. Intell. Robot. Syst., vol. 21, no. 1, pp. 51-71, 1998.
9. R. Schoknecht, M. Spott, and M. Riedmiller, "Fynesse: An architecture for integrating prior knowledge in autonomously learning agents," Soft Comput., vol. 8, no. 6, pp. 397-408, 2004.
10. G. Hailu and G. Sommer, "Integrating symbolic knowledge in reinforcement learning," in Proc. Int. Conf. Syst., Man, Cybern., vol. 2. Oct. 1998, pp. 1491-1496.
11. D. Shapiro, P. Langley, and R. Shachter, "Using background knowledge to speed reinforcement learning in physical agents," in Proc. Int. Conf. Auto. Agents, May 2001, pp. 254-261.
12. A.-H. Tan, "FALCON: A fusion architecture for learning, cognition, and navigation," in Proc. IJCNN, Budapest, Hungary, Jul. 2004, pp. 3297-3302.
13. A.-H. Tan, N. Lu, and X. Dan, "Integrating temporal difference methods and self-organizing neural networks for reinforcement learning with delayed evaluative feedback," IEEE Trans. Neural Netw., vol. 19, no. 2, pp. 230-244, Feb. 2008.
14. G. A. Carpenter and S. Grossberg, "A massively parallel architecture for a self-organizing neural pattern recognition machine," Comput. Vis., Graph., Image Process., vol. 37, no. 1, pp. 54-115, 1987.
15. T.-H. Teng, Z.-M. Tan, and A.-H. Tan, "Self-organizing neural models integrating rules and reinforcement learning," in Proc. IEEE IJCNN, Jun. 2008, pp. 3770-3777.
16. T.-H. Teng and A.-H. Tan, "Cognitive agents integrating rules and reinforcement learning for context-aware decision support," in Proc. IAT, Dec. 2008, pp. 318-321.
17. J. A. MartѤn H., J. De Lope, and D. Maravall, "The kNN-TD reinforcement learning algorithm," in Methods and Models in Artificial and Natural Computation. A Homage to Professor Mira's Scientific Legacy (Lecture Notes in Computer Science), vol. 5601. Berlin, Germany: Springer-Verlag, 2009, pp. 305-314.
18. H. Montazeri, S. Moradi, and R. Safabakhsh, "Continuous state/action reinforcement learning: A growing self-organizing map approach," Neurocomputing, vol. 74, no. 7, pp. 1069-1082, 2011.
19. P. Niyogi, F. Girosi, and T. Poggio, "Incorporating prior information in machine learning by creating virtual examples," Proc. IEEE, vol. 86, no. 11, pp. 2196-2209, Nov. 1998.
20. I. Guyon, A. Saffari, G. Dror, and G. Cawley, "Agnostic learning vs. prior knowledge challenge," in Proc. IJCNN, Orlando, FL, USA, Aug. 2007, pp. 829-834.
21. H. Langseth and T. D. Nielsen, "Fusion of domain knowledge with data for structural learning in object oriented domains," J. Mach. Learn. Res., vol. 4, pp. 339-368, Dec. 2003.
22. R. Mahony and R. Williamson, "Prior knowledge and preferential structures in gradient descent learning algorithms," J.Mach. Learn. Res., vol. 1, no. 4, pp. 311-355, 2001.
23. A. R. Masegosa and S. Moral, "An interactive approach for Bayesian network learning using domain/expert knowledge," Int. J. Approx. Reasoning, vol. 54, no. 8, pp. 1168-1181, 2013.
24. F. Lauer and G. Bloch, "Incorporating prior knowledge in support vector machines for classification: A review," Neurocomputing, vol. 71, nos. 7-9, pp. 1578-1594, 2008.
25. C. Dugas, Y. Bengio, F. Belisle, C. Nadeau, and R. Garcia, "Incorporating functional knowledge in neural networks," J. Mach. Learn. Res., vol. 10, pp. 1239-1262, Dec. 2009.
26. C. J. C. H. Watkins and P. Dayan, "Q-learning," Mach. Learn., vol. 8, no. 3, pp. 279-292, 1992.
27. T.-H. Teng, A.-H. Tan, and Y.-S. Tan, "Self-regulating action exploration in reinforcement learning," Proc. Comput. Sci., vol. 13, pp. 62-74, Oct. 2012.
28. A.-H. Tan, "Direct code access in self-organizing neural networks for reinforcement learning," in Proc. IJCAI, Jan. 2007, pp. 1071-1076.
29. T.-H. Teng and A.-H. Tan, "Knowledge-based exploration for reinforcement learning in self-organizing neural networks," in Proc. IAT, Dec. 2012, pp. 332-339.
30. S. Ficici and J. Pollack, "Statistical reasoning strategies in the pursuit and evasion domain," in Advances in Artificial Life (Lecture Notes in Computer Science), vol. 1674, D. Floreano, J.-D. Nicoud, and F. Mondada, Eds. New York, NY, USA: Springer-Verlag, 1999, pp. 79-88.
31. M. R. Endsley, "Situation awareness: Progress and directions," in A Cognitive Approach to Situation Awareness: Theory and Application. Aldershot, U.K.: Ashgate Pub., 2004, ch. 17, pp. 317-341.
32. E. Tulving, "How many memory systems are there?" Amer. Psychol., vol. 40, no. 4, pp. 385-398, 1985.