Evolutionary optimization of a hierarchical object recognition model

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Volumn 35, Issue 3, 2005, Pages 426-437

  Schneider, Georg ^a,b   Wersing, Heiko ^a   Sendhoff, Bernhard ^a   Körner, Edgar ^a  

^a HONDA RESEARCH INSTITUTE EUROPE GMBH   (Germany)

^b AUDI ELECTRONICS VENTURE GMBH   (Germany)

Author keywords

Biologically motivated vision system; Evolution strategies; Evolutionary optimization; Generalization; Indirect coding; Object recognition

Indexed keywords

COMPUTER VISION; EVOLUTIONARY ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; NEURAL NETWORKS; OPTIMIZATION; PATTERN RECOGNITION SYSTEMS;

BIOLOGICALLY MOTIVATED VISION SYSTEM; EVOLUTION STRATEGIES; EVOLUTIONARY OPTIMIZATION; FIRST AND SECOND ORDER GENERALIZATION; INDIRECT CODING;

OBJECT RECOGNITION;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; AUTOMATED PATTERN RECOGNITION; BIOLOGICAL MODEL; CLUSTER ANALYSIS; COMPARATIVE STUDY; COMPUTER ASSISTED DIAGNOSIS; COMPUTER SIMULATION; EVALUATION; IMAGE ENHANCEMENT; INFORMATION RETRIEVAL; METHODOLOGY; REPRODUCIBILITY; SENSITIVITY AND SPECIFICITY; SIGNAL PROCESSING; STATISTICAL MODEL;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; CLUSTER ANALYSIS; COMPUTER SIMULATION; IMAGE ENHANCEMENT; IMAGE INTERPRETATION, COMPUTER-ASSISTED; INFORMATION STORAGE AND RETRIEVAL; MODELS, BIOLOGICAL; MODELS, STATISTICAL; PATTERN RECOGNITION, AUTOMATED; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY; SIGNAL PROCESSING, COMPUTER-ASSISTED;

EID: 20444369515     PISSN: 10834419     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSMCB.2005.846649     Document Type: Article

References (38)

1. M. Egmont-Petersen, D. de Ridder, and H. Handels, "Image processing with neural networks - A review," Pattern Recognit., vol. 35, no. 10, pp. 2279-2301, 2002.
2. X. Yao, "Evolving artificial neural networks," Proc. IEEE, vol. 87, no. 9, pp. 1423-1447, Sep. 1999.
3. F. Rothlauf, Representations for Genetic and Evolutionary Algorithms. New York: Springer-Verlag, 2002.
4. B. Sendhoff, M. Kreutz, and W. von Seelen, "A condition for the genotype-phenotype mapping: Causality," in Proc. 7th Int. Conf. Genetic Algorithms (ICGA), T. Bäck, Ed., 1997, pp. 73-80.
5. P. Schuster and P. Stadler, "Sequence redundancy in biopolymers: A study on {RNA} and protein structures," in Viral Regulatory Structures, G. Myers, Ed. Reading, MA: Addison-Wesley, 1997. vol. XXVIII of Santa Fe Institute Studies in the Sciences of Complexity.
6. E. T. Rolls and S. M. Stringer, "On the design of neural networks in the brain by genetic evolution," Progr. Neurobiol., vol. 6, no. 61, pp. 557-579, 2000.
7. B. Sendhoff and M. Kreutz, "A model for the dynamic interaction between evolution and learning," Neural Process. Lett., vol. 10, no. 3, pp. 181-193, 1999.
8. S. Quartz and T. Sejnowski, "The neural basis of cognitive development: A constructivist manifesto," Behav. Brain Sci., vol. 9, pp. 537-596, 1997.
9. A. G. Rust, R. Adams, S. George, and H. Bolouri, "Toward computational neural systems through developmental evolution," in Prof. Lecture Notes Comput. Sci. Conf., vol. 2036, S. Wermter, J. Austin, and D. Willshaw, Eds., 2001, pp. 188-202.
10. K. Fukushima, "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position," Biolog. Cybern., vol. 39, pp. 139-202, 1980.
11. G. Wallis and E. T. Rolls, "A model of invariant object recognition in the visual system," Progr. Neurobiol., vol. 51, pp. 167-194, 1997.
12. M. Riesenhuber and T. Poggio, "Hierarchical models of object recognition in cortex," Nature Neurosci., vol. 2, no. 11, pp. 1019-1025, 1999.
13. H. Wersing and E. Körner, "Learning optimized features for hierarchical models of invariant recognition," Neural Comput., vol. 15, no. 7, pp. 1559-1588, 2003.
14. K. Tanaka, "Inferotemperal cortex and object vision: Stimulus selectivity and columnar organization," Annu. Rev. Neurosci., vol. 19, pp. 109-139, 1996.
15. N. K. Logothetis and J. Pauls, "Psychophysical and physiological evidence for viewer-centered object representations in the primate," Cerebral Cortex, vol. 5, pp. 270-288, 1995.
16. S. Thorpe, D. Fize, and C. Marlot, "Speed of processing in the visual system," Nature, vol. 381, pp. 520-522, 1996.
17. E. Körner, M.-O. Gewaltig, U. Körner, A. Richter, and T. Rodemann, "A model of computation in neocortical architecture," Neural Netw., vol. 12, no. 7-8, pp. 989-1005, 1999.
18. H. B. Barlow, "The twelfth Bartlett memorial lecture: The role of single neurons in the psychology of perception," Q. J. Exp. Psych., vol. 37, pp. 121-145, 1985.
19. B. A. Olshausen and D. J. Field, "Sparse coding with an overcomplete basis set: A strategy employed by V1?," Vis. Res., vol. 37, pp. 3311-3325, 1997.
20. A. J. Bell and T. J. Sejnowski, "The 'independent components' of natural scenes are edge filters," Vis. Res., vol. 37, pp. 3327-3338, 1997.
21. P. O. Hoyer and A. Hyvärinen, "A multilayer sparse coding network learns contour coding from natural images," Vis. Res., vol. 42, no. 12, pp. 1593-1605, 2002.
22. H. Wersing and E. Körner, "Unsupervised learning of combination features for hierarchical recognition models," in Proc. Int. Conf. Artifical Neural Networks, J. R. Dorronsoro, Ed., 2002, pp. 1225-1230.
23. T. Serre, M. Riesenhuber, J. Louie, and T. Poggio, "On the role of object-specific features for real world object recognition in biological vision," in Proc. Lecture Notes Computer Science Conf., vol. 2525, H. H. Bülthoff, S. W. Lee, T. A. Poggio, and C. Wallraven, Eds., 2002, pp. 387-397.
24. Z. Pan, T. Sabisch, R. Adams, and H. Bolouri, "Staged training of neocognitron by evolutionary algorithms," in Proc. Congr. Evolutionary Computation, P. J. Angeline, Z. Michalewicz, M. Schoenauer, X. Yao, and A. Zalzala, Eds., 1999, pp. 1965-1972.
25. D. Shi, D. Chunlei, and Y. S. Daniel, "Neocognitron's parameter tuning by genetic algorithms," Int. J. Neural Syst., vol. 9, pp. 497-509, 1999.
26. V. Honavar and L. Uhr, "Brain-structured connectionist networks that perceive and learn," Connect. Sci., vol. 1, pp. 139-160, 1989.
27. M.-Y. Teo and S.-K. Sim, "Training the neocognitron network using design of experiments," Artificial Intelligence in Engineering, vol. 9, no. 2, pp. 85-94, 1995.
28. M.-Y. Teo, L.-P. Khoo, and S.-K. Sim, "Application of genetic algorithms to optimize neocognitron network parameters," Neural Netw. World, vol. 7, no. 3, pp. 293-304, 1997.
29. H. Kitano, "Designing neural networks using genetic algorithms with graph generation system," Complex Syst., vol. 4, pp. 461-476, 1990.
30. A. Topchy and W. F. Punch, "Faster genetic programming based on local gradient search of numeric leaf values," in Proc. Genetic and Evolutionary Computation Conf., vol. 7-11, L. Spector, E. D. Goodman, A. Wu, W. B. Langdon, H.-M. Voigt, M. Gen, S. Sen, M. Dorigo, S. Pezeshk, M. H. Garzon, and E. Burke, Eds., 2001, pp. 155-162.
31. K. Krawiec and B. Bhanu, "Coevolutionary and linear genetic programming for visual learning," in Proc. Genetic and Evolutionary Computation Conf, Jul. 11, 2003, pp. 332-343.
32. H.-P. Schwefel and G. Rudolph, "Contemporary evolution strategies," in Proc. 3rd Eur. Conf. Artificial Life: Advances in Artificial Life, vol. 929, F. Morán. A. Moreno, J. J. Merelo, and P. Chacón, Eds., Jun. 1995, pp. 893-907.
33. T. Bäck, D. B. Fogel, and Z. Michalewicz, Eds., Evolutionary Computation I: Basic Algorithms and Operators. Bristol, U.K.: IOP, 2000.
34. M. Hüsken, J. Gayko, and B. Sendhoff, "Optimization for problem classes - Neural networks that learn to learn," in Proc. IEEE Symp. Combinations of Evolutionary Computation and Neural Networks, X. Yao, Ed., 2000, pp. 98-109.
35. S. K. Nayar, S. A. Nene, and H. Murase, "Real-time 100 object recognition system," in Proc. IEEE Int. Conf. Robotics and Automation, Apr. 1996, pp. 231-235.
36. G. Schneider, H. Wersing, B. Sendhoff, and E. Körner, "Evolutionary feature design for object recognition with hierarchical networks," in Proc. 9th Int. Conf. Neural Information Processing, vol. 4, L. Wang, J. Rajapakse, K. Fukushima, S.-Y. Lee, and X. Yao, Eds., 2002, pp. 1936-1940.
37. G. Hinton and S. Nowlan, "How learning can guide evolution," Complex Syst., vol. 1, pp. 495-502, 1987.
38. D. Roobaert and M. V. Hulle, "View-based 3d object recognition with support vector machines," in Proc. IEEE Int. Workshop on Neural Networks for Signal Processing, 1999, pp. 77-84.