SINBAD automation of scientific discovery: From factor analysis to theory synthesis

Natural Computing

Volumn 3, Issue 2, 2004, Pages 207-233

  Kurşun, Olcay ^a   Favorov, Oleg V ^b  

^a University of Central Florida   (United States)

^b NORTH CAROLINA STATE UNIVERSITY   (United States)

Author keywords

Bayesian networks; Blind source separation; Causal relations; Concept acquisition; Curse of dimensionality; IMAX; Knowledge representation; nonlinear factor analysis; Virtual Scientist

Indexed keywords

ALGORITHM; ANALYTIC METHOD; ARTICLE; AUTOMATION; BRAIN CORTEX; CORRELATION ANALYSIS; DENDRITE; FACTORIAL ANALYSIS; HUMAN; INFORMATION PROCESSING; LEARNING; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL;

EID: 4344705639     PISSN: 15677818     EISSN: None     Source Type: Journal    
DOI: 10.1023/B:NACO.0000027756.50327.26     Document Type: Article

References (29)

1. Becker S (1999) Implicit learning in 3d object recognition: the importance of temporal context. Neural Computation 11: 347-374
2. Becker S (1996) Mutual information maximization: models of cortical self-organization. Network 7(1): 7-31
3. Becker S (1995) JPMAX: learning to recognize moving objects as a model-fitting problem. In: Advances in Neural Information Processing Systems 7, pp 933-940. Morgan Kaufmann Publishers, San Mateo, CA
4. Becker S and Hinton GE (1992) A self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355: 161-163
5. Bishop CM (1995) Neural Networks for Pattern Recognition. Oxford University Press, Oxford
6. Boyen X, Friedman N and Koller D (1999) Discovering the hidden structure of complex dynamic systems. Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (UAI 99), pp. 91-100. Stockholm, Sweden
7. Clark A and Thornton C (1997) Trading places: computation, representation, and the limits of uninformed learning. Behavioral and Brain Sciences 20: 57-90
8. Favorov OV and Ryder D (2004) SINBAD: A neocortical mechanism for discovering environmental variables and regularities hidden in sensory input. Biological Cybernetics (in press)
9. Favorov OV, Ryder D, Hester JT, Kelly DG and Tommerdahl M (2003) The cortical pyramidal cell as a set of interacting error backpropagating networks: a mechanism for discovering nature's order. In: Hecht-Nielsen R and McKenna T (eds) Computational Models for Neuroscience, pp. 25-64. Springer Verlag, London
10. Hanson SJ and Pratt LY (1989) Comparing biases for minimal network construction with backpropagation. In: Touretzky DS (ed) Advances in Neural Information Processing Systems, vol. 1, pp. 177-185. Morgan Kaufmann, San Mateo, CA
11. Hassibi B and Stork DG (1993) Second order derivatives for network pruning: optimal brain surgeon. In: Hanson SJ, Cowan JD, and Giles CL (eds) Advances in Neural Information Processing Systems, vol. 5, pp. 164-171. Morgan Kaufmann, San Mateo, CA
12. Hyvarinen A, Karhunen J and Oja E (2001) Independent Component Analysis. John Wiley & Sons, Toronto
13. Ilin A and Valpola H (2003) On the effect of the form of the posterior approximation in variational learning of ICA models. In Proc. of the 4th Int. Symp. on Independent Component Analysis and Blind Signal Separation (ICA2003), pp. 915-920. Nara, Japan
14. Jordan MI (2004) Graphical models. Statistical Science (to appear)
15. Joshi S, Kursun O and Favorov OV (2003) Exploiting the structure of order: an application to natural images. The 7th World Multiconference on Systemics, Cybernetics and Informatics, Orlando, FL
16. Jutten C and Karhunen J (2003) Advances in nonlinear blind source separation. In Proc. of the 4th Int. Symp. on Independent Component Analysis and Blind Signal Separation (ICA2003), pp. 245-256
17. Kramer MA (1991) Nonlinear principal component analysis using autoassociative neural networks. Aiche Journal 37(2): 233-243
18. Kursun O and Favorov OV (2003) Single-frame super-resolution by inference from learned features. Istanbul University Journal of Electrical & Electronics Engineering 3(1): 673-681
19. Kursun O and Favorov OV (2002) Single-frame super-resolution by a cortex based mechanism using high level visual features in natural images. IEEE Workshop on Applications of Computer Vision, Orlando, FL
20. Lang KJ and Hinton GE (1989) Dimensionality reduction and prior knowledge in e-set recognition. NIPS 1989: 178-185
21. Lappalainen H and Honkela A (2000) Bayesian nonlinear independent component analysis by multi-layer perceptrons. In: Girolami M (ed) Advances in Independent Component Analysis, pp 93-121 Springer-Verlag. MATLAB toolbox is available at http://www.cis.hut.fi/projects/bayes/software/
22. LeCun Y, Denker JS and Solla SA (1990) Optimal brain damage. In: Touretzky DS (ed) Advances in Neural Information Processing Systems, vol. 2, pp. 598-605. Morgan Kaufmann, San Mateo, CA
23. Mjolsness E and DeCoste D (2001) Machine learning for science: state of the art and future prospects. Science 293: 2051-2055
24. Phillips WA and Singer W (1997) In search of common foundations for cortical computation. Behavioral and Brain Sciences 20: 657-722
25. Rumelhart DE, Hinton GE ad Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, Mcclelland JL and PDP Research Group (eds) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318-362. MIT Press, Cambridge, Mass
26. Ryder D (2004) SINBAD Neurosemantics: a theory of mental representation. Mind & Language (in press)
27. Ryder D and Favorov OV (2001) The new associationism: a neural explanation for the predictive powers of cerebral cortex. Brain and Mind 2: 161-194
28. Stone J (1996) Learning perceptually salient visual parameters using spatiotemporal smoothness constraints. Neural Computation 8: 1463-1492
29. Valpola H, Raiko T and Karhunen J (2001) Building blocks for hierarchical latent variable models. Proc. Int. Conf. on Independent Component Analysis and Signal Separation. San Diego