Multidimensional Hebbian Learning with Temporal Coding in Neocognitron Visual Recognition

IEEE Transactions on Systems, Man, and Cybernetics: Systems

Volumn 47, Issue 12, 2017, Pages 3386-3396

  Lee, Yun Parn ^a  

^a MING CHUAN UNIVERSITY   (Taiwan)

Author keywords

Multidimensional signal processing; neocognitron; pattern classification; principal component feature extraction; unsupervised Hebbian learning

Indexed keywords

BINARY IMAGES; BINS; CHARACTER RECOGNITION; NEURAL NETWORKS; OBJECT RECOGNITION; PATTERN RECOGNITION; SIGNAL PROCESSING;

CORRELATION FUNCTION; HEBBIAN LEARNING; MULTIDIMENSIONAL SIGNAL PROCESSING; NEOCOGNITRON; NEURAL NETWORK MODEL; PRINCIPAL COMPONENTS; SYNAPTIC EFFICIENCY; VISUAL RECOGNITION;

PRINCIPAL COMPONENT ANALYSIS;

EID: 85040688769     PISSN: 21682216     EISSN: 21682232     Source Type: Journal    
DOI: 10.1109/TSMC.2016.2599200     Document Type: Article

References (48)

1. M. M. Menon and K. G. Heienmann, "Classification of patterns using a self-organizing neural network, " Neural Netw., vol. 1, no. 3, pp. 201-215, 1988.
2. E. Barnard and D. Casasent, "Shift invariance and the neocognitron, " Neural Netw., vol. 3, no. 4, pp. 403-410, 1990.
3. T. H. Hildebrandt, "Optimal training of thresholded linear correlation classifiers, " IEEE Trans. Neural Netw., vol. 2, no. 6, pp. 577-588, Nov. 1991.
4. C. Ting and K.-C. Chung, "An adaptive algorithm for neocognitron to recognize analog images, " Neural Netw., vol. 6, no. 2, pp. 285-299, 1993.
5. L. Wan, D. Li, W. G. Wee, C.-Y. Han, and D. T. Porembka, "ANN approach for 2-D echocardiographic image processing-Application of neocognitron model to LV boundary formation, " in Applications of Artificial Neural Networks II, vol. 1469, S. K. Rogers, Ed. SPIE, Apr. 1991, pp. 432-440. [Online]. Available: http://proceedings. spiedigitallibrary. org/proceeding. aspx?articleid=963163
6. D. Li, M. R. Spicer, and W. G. Wee, "Training a neocognitron neural network for gray level images, " in Proc. Int. Neural Netw. Conf., vol. 1. Paris, France, Jul. 1990, pp. 11-14.
7. J. Rajapakese and R. Acharya, "Medical image segmentation with MARA, " in Proc. IEEE Int. Joint Conf. Neural Netw., vol. 2. San Diego, CA, USA, Jun. 1990, pp. 965-972.
8. J. Gilmore and A. Czuchry, "An application of the neocognitron in target recognitron, " in Proc. Int. Neural Netw. Conf., vol. 1. Paris, France, Jul. 1990, pp. 15-18.
9. S.-D. Wang and C.-C. Pan, "A neural network approach for Chinese character recognition, " in IEEE Proc Int. Joint Conf. Neural Netw., vol. 2. San Diego, CA, USA, Jun. 1990, pp. 917-923.
10. E. J. Kim and Y. Lee, "Handwritten Hangul recognition using a modified neocognitron, " Neural Netw., vol. 4, no. 6, pp. 743-750, 1991.
11. B. A. White and M. I. Elmasry, "The digi-neocognitron: A digital neocognitron neural network model for VLSI, " IEEE Trans. Neural Netw., vol. 3, no. 1, pp. 73-85, Jan. 1992.
12. J. I. Minnix, E. S. McVey, and R. M. Inigo, "Modified neocognitron with position normalizing preprocessor for translation invariant shape recognition, " in Proc. IEEE Int. Joint Conf. Neural Netw., vol. 1. San Diego, CA, USA, Jun. 1990, pp. 395-400.
13. Q. Xu et al., "A fault tolerance analysis of a neocognitron model, " in Proc. Int. Joint Conf. Neural Netw., Washington, DC, USA, Jan. 1990, pp. II559-II562.
14. C.-H. Sung and D. Wilson, "Perconitron: Neocognitron coupled with perceptron, " in Proc. IEEE Int. Joint Conf. Neural Netw., vol. 3. San Diego, CA, USA, Jun. 1990, pp. 753-758.
15. K. Johnson, C. Daniell, and J. Burman, "Feature extraction in the neocognitron, " in Proc. IEEE Int. Conf. Neural Netw., vol. 2. 1988, pp. 117-126.
16. D. Shi, C. Dong, and D. S. Yeung, "Neocognitron's parameter tuning by genetic algorithms, " Int. J. Neural Syst., vol. 9, no. 6, pp. 497-509, 1999.
17. H. Wersing and E. Körner, "Learning optimized features for hierarchical models of invariant object recognition, " Neural Comput., vol. 15, no. 7, pp. 1559-1588, 2003.
18. I. Bax, G. Heidermann, and H. Ritter, "A hierarchical feed-forward network for object detection tasks, " Opt. Eng., vol. 45, no. 6, 2006, Art. no. 067203. [Online]. Available: http://opticalengineering. spiedigitallibrary. org/article. aspx?articleid=1076727
19. T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio, "Robust object recognition with cortex-like mechanisms, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 3, pp. 411-426, Mar. 2007.
20. K. Fukushima, S. Miyake, and T. Ito, "Neocognitron: A neural network model for a mechanism of visual pattern recognition, " IEEE Trans. Syst., Man, Cybern., vol. SMC-13, no. 5, pp. 826-834, Sep. /Oct. 1983.
21. K. Fukushima and S. Miyake, "Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position, " Pattern Recognit., vol. 15, no. 6, pp. 455-469, 1982.
22. K. Fukushima, "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, " Biol. Cybern., vol. 36, no. 4, pp. 193-202, 1980.
23. K. Fukushiam, "Cognitron: A self-organizing multilayered neural network, " Biol. Cybern., vol. 20, no. 3, pp. 121-136, 1975.
24. A. Y. Cheng and D. S. Yeung, "Sensitivity analysis of neocognitron, " IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 29, no. 2, pp. 238-249, May 1999.
25. M.-T. Teo and S.-K. Sim, "Training the neocognitron network using design of experiments, " Artif. Intell. Eng., vol. 9, no. 2, pp. 85-94, 1995.
26. K. Fukushima, "Increasing robustness against background noise: Visual pattern recognition by a neocognitron, " Neural Netw., vol. 24, no. 7, pp. 767-778, 2011.
27. Y. Hatakeyama and Y. Kakazu, "Detecting a target object using an expanded neocognitron, " Math. Comput. Model., vol. 21, nos. 1-2, pp. 173-183, Jan. 1995.
28. A. Cardoso and A. Wichert, "Neocognitron and the map transformation cascade, " Neural Netw., vol. 23, no. 1, pp. 74-88, 2010.
29. D. R. Lovell, T. Downs, and A. C. Tsoi, "An evalution of the neocognitron, " IEEE Trans. Neural Netw., vol. 8, no. 5, pp. 1090-1105, Sep. 1997.
30. C. Neubauer, "Evaluation of convolutional neural networks for visual recognition, " IEEE Trans. Neural Netw., vol. 9, no. 4, pp. 685-696, Jul. 1998.
31. K. Fukushima, "Artificial vision by multi-layered neural networks: Neocognitron and its advances, " Neural Netw., vol. 37, pp. 103-119, Jan. 2013.
32. Hebbian Theory. [Online]. Available: http://en. wikipedia. org/wiki/ Hebbian-learning
33. W. Geerstner and W. M. Kistler, "Mathematical formulations of Hebbian learning, " Biol. Cybern., vol. 87, nos. 5-6, pp. 404-415, 2002.
34. E. R. Kandel, Principals of Neural Science. New York, NY, USA: Elsevier Sci., 1985, ch. 29.
35. D. H. Hubel and T. N. Wiesel, "Receptive fields, binocular interaction and functional architecture in the cat's visual cortex, " J. Physiol., vol. 160, no. 1, pp. 106-154, 1962.
36. D. H. Hubel and T. N. Wiesel, "Functional architecture of macaque monkey visual cortex, " Proc. Roy. Soc. Lond B., vol. 198, no. 1130, pp. 1-59, May 1977.
37. S. Grossberg and E. Mingolla, "Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations, " Perception Psychophys., vol. 38, no. 2, pp. 141-171, 1985.
38. A. Dobbins, S. W. Zucker, and M. S. Cynader, "Endstoping and curvature, " Vis. Res., vol. 29, no. 10, pp. 1371-1387, 1989.
39. J. Malik and P. Perona, "Preattentive texture discrimination with early vision mechanisms, " J. Opt. Soc. America A, vol. 7, no. 5, pp. 923-932, 1990.
40. J. Sklansky and G. N. Wassel, Pattern Classifiers and Trainable Machine. New York, NY, USA: Springer-Verlag, 1991.
41. J. T. Tou and R. C. Gonzalez, Pattern Recognition Principles. Reading, MA, USA: Addision-Wesley, 1974.
42. E. Oja, H. Ogawa, and J. Wangviwattana, "Principal component analysis by homogeneous neural networks, part I: The weighted subspace criterion, " IEICE Trans. Inf. Syst., vol. E75-D, no. 3, pp. 366-382, 1992.
43. E. Oja and J. Karhunen, "On stochastic approximation of the eigenvectors and eigenvalues of the exception of a random matrix, " J. Math. Anal. Appl., vol. 106, pp. 69-84, 1985.
44. L. Xu and A. Yuille, "Robust PCA learning rules based on statistical physics approach, " in Proc. Int. Joint Conf. Neural Netw., vol. 1. Baltimore, MD, USA, 1992, pp. 812-823.
45. T. Y. P. Lee and C. C. Guest, "Modified Hebbian unsupervised learning for large object classes using neocognitron visual recognition, " in Proc. SPIE, vol. 1766. San Diego, CA, USA, 1992, pp. 106-117.
46. K. Johnson, Rockwell International Science Center, Internal Report with Permission to use, private communication, 1989.
47. Y. P. Lee, "Multiplayer neural network vision model for pattern recognition and stereo vision, " Ph. D. dissertation, Dept. Elect. Comput. Eng., Univ. California at San Diego, San Diego, CA, USA, 1995.
48. Principal Component Analysis. [Online]. Available: https:// en. wikipedia. org/wiki/Principal-component-analysis