From synapses to rules

Cognitive Systems Research

Volumn 3, Issue 2, 2002, Pages 167-201

  Apolloni, B ^a   Malchiodi, D ^a   Orovas, C ^a   Palmas, G ^b  

^a UNIVERSITY OF MILAN   (Italy)

^b STMICROELECTRONICS   (Italy)

Author keywords

Fuzzy relaxations; Hybrid systems; Learning fitness; Rule extraction; Symbolic feedbacks; Understandable learning

Indexed keywords

ACCURACY; ALGORITHM; ANALYTICAL ERROR; ANALYTICAL PARAMETERS; ARTIFICIAL NEURAL NETWORK; AUDITORY STIMULATION; CALCULATION; CLASSIFICATION; CONTROLLED STUDY; DATA ANALYSIS; EMOTION; ENTROPY; HYPOTHESIS; LEARNING; PRIORITY JOURNAL; PROBABILITY; REVIEW; SOCIAL INTERACTION; STATISTICAL ANALYSIS; SYMBOLISM; THEORETICAL MODEL; VISUAL STIMULATION;

EID: 2442501174     PISSN: 13890417     EISSN: None     Source Type: Journal    
DOI: 10.1016/S1389-0417(01)00057-2     Document Type: Article

References (36)

1. Akaike H. A new look at the statistical model identification IEEE Transactions on Automatic Control 19 1985 716-723
2. Andrews R. Geva S. Rule extraction from constrained error backpropagation mlp Proc. 5th Australian Conference on Neural Networks, Queensland 1994 9-12
3. Andrews R. Geva S. Inserting and extracting knowledge from constrained backpropagation network Proc. 6th Australian Conference on Neural Networks, Sidney 1995 29-32
4. Apolloni, B., Baraghini, F., & Palmas, G. (2000a). PAC meditation on boolean formulas. Technical report, Università degli Studi di Milano.
5. Apolloni B. Chiaravalli S. Pac learning of concept classes through the boundaries of their items Theoretical Computer Science 172 1997 91-120
6. Apolloni B. Malchiodi D. Gaining degrees of freedom in subsymbolic learning Theoretical Computer Science 255 2001 295-321
7. Apolloni B. Malchiodi D. Orovas C. Palmas G. From synapses to rules Foundations of Connectionist-symbolic Integration: Representation, Paradigms, and Algorithms - Proceedings of the 14th European Conference on Artifical Intelligence 2000
8. Apolloni, B., Orovas, C., Taylor, J. G., Fellenz, W., Gielen, S., & Westerdijk, M. (2000c) A general framework for symbol and rule extraction in neural networks. In Amari, S., Lee Giles, C., Gori, M., & Piari, V., editors, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks - IJCNN 2000, pp. II-87, II-92, Los Alamitos. IEEE Computer Society. IEEE Transactions on Neural Networks, submitted.
9. Apolloni B. Ronchini G. Dynamic sizing of multilayer perceptrons Biological Cybernetics 71 1994 49-63
10. Apolloni B. Zoppis I. Subsymbolically managing pieces of symbolical functions for sorting IEEE Transactions on Neural Networks 10 5 1999 1099-1122
11. Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford: Clarendon Press.
12. Blumer A. Ehrenfreucht A. Haussler D. Warmuth M. Learnability and the Vapnik-Chervonenkis dimension Journal of the ACM 36 1989 929-965
13. Cover, T. - Thomas, J. (1991). Elements of Information Theory. New York: Wiley.
14. Cox, E., (1998). The Fuzzy Systems Handbook. San Diego, CA: AP Professional.
15. Craven M. Shavlic J. Extracting tree-structured representations of trained networks Advances in Neural Information Processing Systems 1996 MIT PressCambridge, MA
16. Doffner, G., & Prem, E. (1993). Connectionism, symbol grounding, and autonomous agents. In Proc. 19th ACM Symp. Theory of Computing. Boulder, CO, pp. 144-148.
17. Gallant S. Connectionist expert systems Communications of the ACM 31 2 1998 152-169
18. Geisser, S., (1993). Predictive inference: an introduction. New York: Chapman and Hall.
19. Li, M., & Vitànyi, P. (1993). An introduction to Kolmogorov complexity and its applications. Berlin: Springer.
20. Murata N. Yoshizawa S. Amari S. Network information criterion-determining the number of hidden units for an artificial neural network model IEEE Transactions on Neural Networks 5 1995 865-872
21. Papadimitriou, C. H., (1994). Computational complexity. Reading, MA: Addison-Wesley.
22. Pitt L. Valiant L. Computational limitations on learning from examples Journal of the ACM 35 4 1988 965-984
23. Pollack J. Recursive distributed representations Artificial Intelligence 1-2 45 1990 77-105
24. Qunilan J.R. C4.5: programs for machine learning 1993 Morgan KaufmannSan Mateo, CA
25. Rissanen J. A universal prior for integers and estimation by minimum description length Annals of Statistics 11 2 1983 416-431
26. Roger H. Theory of recoursive functions and effective computability 1967 McGraw-HillNew York
27. Rohatgi V.K. An introduction to probability theory and mathematical statistics Wiley series in probability and mathematical statistics 1976 John Wiley - SonsNew York
28. Rumelhart D.E. Hinton G.E. Williams R.J. Learning internal representations by error propagation 1986 318-362 MIT Press Cambridge, MA Chapter 8
29. Sahni S. Some related problems from network flows, game theory, and integer programming Proc. of the 13th Annual IEEE Symp. on Switching and Automata Theory 1972 130-138
30. The PHYSTA project (2001) Principled hybrid systems: theory and applications (physta). Retrieved June 6 2001 from http://www.image.ece.ntua.gr/physta.
31. Tickle A. Andrews R. Golea M. Diederich J. The truth will come to light: Directions and challenges in extracting the knowledge embedded within trained artificial neural networks IEEE Transactions on Neural Networks 9 1998 1057-1068
32. Towell G. Shavlic J. Noordewier M. Refinement of approximately correct domain theories by knowledge-based neural networks Proc. of the Eight National Conference on Artificial Intelligence, San Jose, CA 1990 177-182 AAAI Press
33. Vapnik V.1982 SpringerNew York
34. Vapnik V. The nature of statistical learning theory 1995 SpringerNew York
35. Wegener I. The complexity of boolean functions 1987 Teubner and WileyNew York
36. Wilks S.S. Mathematical statistics Wiley publications in statistics 1962 John WileyNew York