Could knowledge-based neural learning be useful in developmental robotics? The case of KBCC

International Journal of Humanoid Robotics

Volumn 4, Issue 2, 2007, Pages 245-279

  Shultz, Thomas R ^a   Rivest, François ^b   Egri, László ^a   Thivierge, Jean Philippe ^b   Dandurand, Frédéric ^a  

^a MCGILL UNIVERSITY   (Canada)

^b UNIVERSITÉ DE MONTRÉAL   (Canada)

Author keywords

Developmental robotics; Knowledge transfer; Knowledge based learning; Neural networks

Indexed keywords

ANALOGICAL REASONING; DEVELOPMENTAL ROBOTICS; KNOWLEDGE TRANSFER; KNOWLEDGE-BASED CASCADE-CORRELATION (KBCC);

KNOWLEDGE BASED SYSTEMS; LEARNING ALGORITHMS; LEARNING SYSTEMS; NEURAL NETWORKS; NEUROLOGY;

ROBOTICS;

EID: 34447319909     PISSN: 02198436     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0219843607001035     Document Type: Article

References (95)

1. J. Weng, J. McClelland, A. Pentland, O. Sporns, I. Stockman, M. Sur and E. Thelen, Autonomous mental development by robots and animals, Science 291 (2000) 599-600.
2. F.-F. Li, Knowledge transfer in learning to recognize visual object classes, in Proc. 5th Int. Conf. Development and Learning ICDL 2006 Department of Psychological and Brain Sciences, Bloomington, Indiana, USA (2006).
3. J. Weng, Developmental robotics: Theory and experiments, Int. J. Humanoid Robot. 1 (2004) 199-236.
4. T. R. Shultz and F. Rivest, Knowledge-based cascade-correlation: Using knowledge to speed learning, Connect. Sci. 13 (2001) 1-30.
5. N. Chater, J. B. Tenenbaum and A. Yuille, Probabilistic models of cognition: Conceptual foundations, Trends Cogn. Sci. 1 (2006) 287-291.
6. J. L. Elman, E. A. Bates, M. H. Johnson, A. Karmiloff-Smith, D. Parisi and K. Plunkett, Rethinking Innateness: A Connectionist Perspective on Development (MIT Press, Cambridge, MA, 1996).
7. T. R. Shultz, Computational Developmental Psychology (MIT Press, Cambridge, MA, 2003).
8. A. Robins, Transfer in cognition, Connect. Sci. 8 (1996) 185-203.
9. G. Nakamura, Knowledge-based classification of ill-defined categories, Mem. Cogn. 13 (1985) 377-384.
10. E. Heit, Models of the effects of prior knowledge on category learning, J. Exp. Psychol. Learn. Mem. Cogn. 20 (1994) 1264-1282.
11. F. C. Keil, Conceptual development and category structure, in Concepts and Conceptual Development: Ecological and Intellectual Factors in Categorization, ed. U. Neisser, (Cambridge University Press, Cambridge, 1987).
12. G. L. Murphy, A rational theory of concepts, Psychol. Learn. Motiv. 29 (1993) 327-359.
13. M. J. Pazzani, Influence of prior knowledge on concept acquisition: Experimental and computational results, J. Exp. Psychol. Learn. Mem. Cogn. 17 (1991) 416-432.
14. E. J. Wisniewski, Prior knowledge and functionally relevant features in concept learning, J. Exp. Psychol. Learn. Mem. Cogn. 21 (1995) 449-468.
15. S. E. Fahlman and C. Lebiere, The cascade-correlation learning architecture, in Advances in Neural Information Processing systems 2 ed. D. S. Touretzky (Morgan Kaufmann, Los Altos, CA, 1990), pp. 524-532.
16. L. Y. Pratt, Discriminality-based transfer between neural networks, in Advances in Neural Information Processing Systems 5 (Morgan Kaufmann, San Mateo, CA, 1993), pp. 204-211.
17. R. Caruana, Multitask learning, Mach. Learn. 28 (1997) 41-75.
18. S. Thrun and T. Mitchell, Integrating inductive neural network learning and explanation-based learning, in Proc. 13th Int. Joint Conf. Artificial Intelligence, ed. R. Bajcsy (Morgan Kaufmann, San Mateo, CA, USA, 1993).
19. D. Silver and R. Mercer, The parallel transfer of task knowledge using dynamic learning rates based on a measure of relatedness, Connect. Sci. 8 (1996) 277-294.
20. J. W. Shavlik, A framework for combining symbolic and neural learning, Mach. Learn. 14 (1994) 321-331.
21. M. I. Jordan and R. A. Jacobs, Hierarchical mixtures of experts and the EM algorithm, Neural. Comput. 6 (1994) 181-214.
22. A. Clark and C. Thornton, Trading spaces: Computation, representation and the limits of uninformed learning, Behav. Brain Sci. 20 (1997) 57-97.
23. S. E. Fahlman, Faster-learning variations on back-propagation: An empirical study, in Proc. 1988 Connectionist Models Summer School eds. D. S. Touretzky, G. E. Hinton and T. J. Sejnowski (Morgan Kaufmann, Los Altos, CA, 1988), pp. 38-51.
24. J. A. Fodor and Z. W. Pylyshyn, Connectionism and cognitive architecture: A critical analysis, Cognition 28 (1988) 3-71.
25. S. Pinker, How the Mind Works (Norton New York, 1997).
26. F. Rivest and T. R. Shultz, Compositionality in a knowledge-based constructive learner, in Papers from the 2004 AAAI Fall Symp., Menlo Park, CA, USA (AAAI Press, 2004), pp. 54-58.
27. P. Rivest and T. R. Shultz, Application of knowledge-based cascade-correlation to vowel recognition, IEEE Int. Conf. Neural Networks, Hawaii (IEEE Press, 2002) pp. 53-58.
28. J. P. Thivierge and T. R. Shultz, Finding relevant knowledge: KBCC applied to splice-junction determination, IEEE Int. Conf. Neural Networks, Hawaii (IEEE Press, 2002) 1401-1405.
29. G. G. Towell and J. W. Shavlik, Extracting refined rules from knowledge-based neural networks, Mach. Learn. 13 (1993) 71-101.
30. J. P. Thivierge, F. Dandurand and T. R. Shultz, Transferring domain rules in a constructive network: Introducing RBCC, in Proc. IEEE Int. Joint Conf. Neural Networks, Budapest, Hungary (2004), pp. 1403-1409.
31. T. Nagell, Introduction to Number Theory (Wiley, New York, 1951).
32. L. Egri and T. R. Shultz, A compositional neural-network solution to prime-number testing, in Proc. 28th Ann. Conf. Cognitive Science Society, Vancouver, Canada (Erlbaum, Mahwah, NJ, 2006), pp. 1263-1268.
33. S. Baluja and S. E. Fahlman, Reducing network depth in the cascade-correlation learning architecture, School of Computer Science, Carnegie Mellon University, Technical Report, CMU-CS-94-209 (1994).
34. J. Pollack, Recursive distributed representations, Artif. Intell. 46 (1990) 77-105.
35. T. van Gelder, Compositionality: A connectionist variation on a classical theme, Cogn. Sci. 14 (1990) 355-364.
36. R. S. Siegler, Three aspects of cognitive development, Cogn. Psychol. 8 (1976) 481-520.
37. T. R. Shultz, D. Mareschal and W. C. Schmidt, Modeling cognitive development on balance scale phenomena, Mach. Learn. 16 (1994) 57-86.
38. M. Schmitt, On the complexity of computing and learning with multiplicative neural networks, Neural Comput. 14 (2001) 241-301.
39. J. Boom, H. Hoijtink and S. Kunnen, Rules in the balance: Classes, strategies, or rules for the balance scale task, Cog. Dev. 16 (2001) 717-735.
40. B. R. J. Jansen and H. L. J. van der Maas, Statistical test of the rule assessment methodology by latent class analysis, Deve. Rev. 17 (1997) 321-357.
41. B. R. J. Jansen and H. L. J. van der Maas, The development of children's rule use on the balance scale task, J. Exp. Child Psychol. 81 (2002) 383-416.
42. A. L. McCutcheon, Latent Class Analysis (Sage, Newbury Park, 1987 ).
43. S. Pinker, The Language Instinct (Harper Collins, New York, 1994).
44. E. S. Spelke, Initial knowledge: Six suggestions, Cognition 50 (1994) 431-445.
45. K. Wynn, Addition and subtraction by human infants, Nature 358 (1992) 749-750.
46. I. Biederman, Recognition-by-components: A theory of human image interpretation, Psychol. Rev. 94 (1987) 115-147.
47. J. E. Hummel and I. Biederman, Dynamic binding in a neural network for shape recognition, Psychol. Rev. 99 (1992) 480-517.
48. J. M. Anglin, Vocabulary development: A morphological analysis, Monogr. Soc. Res. Child Dev. 58 (1993).
49. B. Goldfield and J. S. Reznick, Early lexical acquisition: Rate, content and vocabulary spurt, J. Child Lang. 17 (1990) 171-183.
50. G. A. Miller, The Science of Words (Freeman New York, 1991).
51. A. L. Woodward, E. M. Markman and C. M. Fitzsimmons, Rapid word learning in 13- and 18-month-olds, Dev. Psychol. 30 (1994) 553-566.
52. T. H. Heibeck and E. M. Markman, Word learning in children: An examination of fast mapping, Child Der. 58 (1987) 1021-1034.
53. W. V. O. Quine, Word and Object (MIT Press Cambridge, MA, 1960).
54. E. M. Markman, Categorization and Naming in Children: Problems of Induction (Cambridge University Press, Cambridge, MA, 1989).
55. P. Gordon, Level-ordering in lexical development, Cognition 21 (1986) 73-93.
56. T. R. Haskell, M. C. MacDonald and M. S. Seidenberg, Language learning and innateness: Some implications of compounds research, Cogn. Psychol. 47 (2003) 119-163.
57. J. Baxter, Learning internal representations, in Proc. 8th Int. Conf. Computational Learning Theory, Santa Cruz, CA, USA (ACM Press, 1995).
58. A. Karmiloff-Smith, Beyond Modularity: A Developmental Perspective on Cognitive Science (MIT Press, Cambridge, MA, 1992).
59. R. Pfeifer and C. Scheier, Understanding Intelligence (MIT Press, Cambridge, MA, 1999).
60. R. D. Beer, Toward the evolution of dynamical neural networks for minimally cognitive behavior, in From Animals to Animats: Proc. 4th Int. Conf. Simulation of Adaptive Behavior, eds. P. Maes, M. Mataric, J.-A. Meyer, J. Pollack and S. W. Wilson (MIT Press, Cambridge, MA, 1996), pp. 421-429.
61. S. Nolfi, Adaptation as a more powerful tool than decomposition and integration, in Proc. Workshop on Evolutionary Computing and Machine Learning, 13th Int. Conf. Machine Learning, eds. T. Fogarty and G. Venturini (1996).
62. T. R. Shultz and F. Rivest, Using knowledge to speed learning: A comparison of knowledge-based cascade-correlation and multi-task learning, in Proc. 7th Int. Conf. Machine Learning (Morgan Kaufmann, San Francisco, 2000), pp. 871-878.
63. R. French, Semi-distributed representations and catastrophic forgetting in connectionist networks, Connect. Sci. 4 (1992) 365-377.
64. T. R. Shultz, F. Dandurand and Y. Takane, Rule following and rule use in simulations of the balance-scale task, submitted.
65. J. A. Fodor, The Modularity of Mind (MIT Press, Cambridge, MA, 1983).
66. P. Gallinari, Training of modular neural net systems, in The Handbook of Brain Theory and Neural Networks, ed. M. A. Arbib (MIT Press, Cambridge, MA, 1995).
67. D. Gentner, Structure mapping: A theoretical framework for analogy, Cogn. Sci. 7 (1983) 155-170.
68. J. Kolodner, Case-Based Reasoning (Morgan Kaufmann, San Mateo, 1993).
69. T. R. Shultz, S. P. Mysore and S. R. Quartz, Why let networks grow? in Neuroconstructivism: Perspectives and Prospects, Vol. 2, eds. S. S. D. Mareschal and G. Westermann (Oxford University Press, Oxford, 2006), pp. 65-98.
70. J. P. Thivierge, F. Rivest and T. R. Shultz, A dual-phase technique for pruning constructive networks, in IEEE Int. Joint Conf. Neural Networks (2003), pp. 559-564.
71. K. Friston, Learning and inference in the brain, Neural Networks 16 (2003) 1325-1352.
72. F. G. Ashby, L. A. Alfonso-Reese, A. U. Turken and E. M. Waldron, A neuropsychological theory of multiple systems in category learning, Psychol. Rev. 105 (1998) 442-481.
73. M. A. Erickson and J. K. Kruschke, Rules and exemplars in category learning, J. Exp. Psychol. Gen. 127 (1998) 107-140.
74. T. J. Palmeri and R. M. Nosofsky, Generalizations by rule models and exemplar models of category learning, in Proc. 5th Annual Meeting of the Cognitive Science Society (Erlbaum, Hillsdale, 1993), pp. 794-799.
75. A. Vandierendonck, A parallel rule activation and rule synthesis model for generalization in category learning, Psychonom. Bull. Rev. 2 (1995) 442-459.
76. J. P. Thivierge, D. Titone and T. R. Shultz, Simulating frontotemporal pathways involved in lexical ambiguity resolution, in Proc. 27th Ann. Conf. Cognitive Science Society (Erlbaum, Mahwah, NJ, 2005), pp. 2178-2183.
77. R. Desimone and J. Duncan, Neural mechanisms of selective visual attention, Ann. Rev. Neurosci. 18 (1995) 193-222.
78. E. K. Miller and J. D. Cohen, An integrative theory of prefrontal cortex function, Ann. Rev. Neurosci. 24 (2001) 167-202.
79. A. D. Wagner, E. J. Pare-Blagoev, J. Clark and R. A. Poldrack, Recovering meaning: Left prefrontal cortex guides controlled semantic retrieval, Neuron 31 (2001) 329-338.
80. S. R. Quartz, Neural networks, nativism and the plausibility of constructivism, Cognition 48 (1993) 223-242.
81. D. Mareschal and T. R. Shultz, Generative connectionist networks and constructivist cognitive development, Cogn. Deve. 11 (1996) 571-603.
82. J. Fodor, On the impossibility of learning "more powerful" structures, in The Debate Between Jean Piaget and Noam Chomsky, ed. M. Piatelli-Palmarini (Routledge & Kegan Paul, 1980), pp. 142-152.
83. M. L. Gick and K. J. Holyoak, Schema induction and analogical transfer, Cogn. Psychol. 15 (1983) 1-38.
84. M. L. Gick and K. J. Holyoak, Analogical problem solving, Cogn. Psychol. 12 (1980) 306-355.
85. G. Rizzolatti and L. Craighero, The mirror-neuron system, Ann. Rev. Neurosci. 27 (2004) 169-192.
86. R. W. Byrne and A. E. Russon, Learning by imitation: A hierarchical approach, Behav. Brain Sci. 21 (1998) 667-721.
87. K. Nader, G. E. Schafe and J. E. LeDoux, Fear memories require protein synthesis in the amygdala for reconsolidation after retrieval, Nature Med. 406 (2000) 722-726.
88. T. Kohonen, Self-Organization and Associative Memory, 2nd edn. (Springer-Verlag New York, 1988).
89. J. Weng and W.-S. Hwang, Online image classification using IHDR, Int. J. Doc. Anal. Recogn. 5 (2003) 118-125.
90. R. Sun, P. Slusarz and C. Terry, The interaction of the explicit and the implicit in skill learning: A dual-process approach, Psychol. Rev. 112 (2005) 159-192.
91. R. M. Neal, Learning stochastic feedforward networks, Department of Computer Science, University of Toronto (1990).
92. F. Rivest and D. Precup, Combining TD-learning with cascade-correlation networks, in Proc. 20th Int. Conf. Machine Learning (AAAI Press, 2003), pp. 632-639.
93. S. Thrun, Towards programming tools for robots that integrate probabilistic computation and learning, in Proc. IEEE, Int. Conf. Robotics and Automation (IEEE, San Franciso, 2000).
94. R. Brooks, Elephants don't play chess, Autonom. Robots 6 (1990) 3-15.
95. S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach 2nd edn. (Prentice Hall, Upper Saddle River, NJ, 2003).