Abstract
Neocognitron, which was proposed by Fukushima, is recently studied in several styles. In this paper, we introduce these studies from the both engineering and biological sides. From the engineering side, we discussed about the ability of the pattern classifier of the Neocognitron and relationship to the “convolutional net”, which is recently well studied in the field of pattern recognition. From the biological side, we tried to explain the recent result of a biological experiment with the Neocognitron, and compare it with another model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36(4), 193–202 (1980)
Fukushima, K., Miyake, S.: Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recognition 15(6), 455–469 (1982)
Fukushima, K.: Neocognitron: A hierahical neural network capable of visual pattern recognition. Neural Networks 1, 119–130 (1988)
Fukushima, K., Wake, N.: Handwritten alphanumeric character recognition by the neocognitron. IEEE Trans. Neural Networks 2(3), 355–365 (1991)
Fukushima, K., Tanigawa, M.: Use of different threshold in learning and recognition. Neurocomputing 11(1), 1–17 (1996)
Shouno, H., Fukushima, K., Okada, M.: Recognition of Handwritten Digits in the Real World by Neocognitron. In: Intelligent Techniques in Character Recognition: Practical Applications, CRC Press, Boca Raton (1998)
LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R.: Handwritten digit recognition with a back-propagation network. In: NIPS, vol. 2 (1990)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Huang, F.J., LeCun, Y.: Large-scale learning with svm and convolutional netw for generic object recognition. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2006, IEEE Computer Society, Los Alamitos (2006)
Logothetis, N.K., Sheinberg, D.L.: Visual object recognition. Annual Review of Neuroscience 19, 577–621 (1996)
Logothetis, N.K., Pauls, J., Poggio, T.: Spatial reference frames for object recognition: Tuning for rotation in depth. Technical report, M.I.T A.I Memo (1995)
Lovell, D.R., Downs, T., Tsoi, A.C.: An evaluation of the neocognitron. IEEE Transactions on Neural Networks 8(5), 1090–1105 (1997)
Satoh, S., Kuroiwa, J., Aso, H., Miyake, S.: A rotation-invariant neocognitron. Systems and Computers in Japan 30(4), 31–40 (1999)
Fukushima, K.: Interpolating vectors for robust pattern recognition. Neural Networks (2007)
Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)
Simard, P.Y., Victorri, B., LeCun, Y., Denker, J.: Tangent prop - a formalism for specifying selected invariances in an adaptive network. In: Tourtezky, D.S., Lippman, R. (eds.) Advances in Neural Information Processing Sytems, vol. 4, pp. 895–903 (1992)
Simard, P.Y., LeCun, Y., Denker, J.: Advances in Neural Information Processings. In: Cowan, S.J.H.J.D., Giles, C.L. (eds.), vol. 5, pp. 50–58 (1993)
Rumelhart, D.E., McClelland, J.L., Group, P.R.: Parallel Distributed Processing: Explorations in Microstructure of Cognition. MIT Press, Cambridge (1986)
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J.Physiol. 106(1), 106–154 (1962)
Yoshizuka, T., Shouno, H., Miyamoto, H., Okada, M., Fukushima, K.: Modeling visual ventarl pathway based on the neocognitron (in Japanese). The Brain & Neural Networks (to be appeared, 2007)
Riesenhuber, M., Poggio, T.: Hierachical modesl of object recognition in cortex. Nature Neuroscience 2, 1019–1025 (1999)
Bricolo, E., Poggio, T., Logothetis, N.K.: 3d object recognition: A model of view-tuned neurons. Advances in Neural Information Processing System 9, 41–47 (1996)
Rolls, E.T.: Brain mechanisms for invariant visual recognition and learning. Behavioural Processes 33, 113–138 (1994)
Fukushima, K.: Neural network model for selective attention in visual pattern recogition and associative recall. Applied Optics 26(23), 4985–4992 (1987)
Shouno, H., Fukushima, K.: Connected character recognition in cursive handwriting using selective attention model with bend processing. Systems and Computers in Japan 26(10), 35–46 (1995)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shouno, H. (2008). Recent Studies Around the Neocognitron. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_109
Download citation
DOI: https://doi.org/10.1007/978-3-540-69158-7_109
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69154-9
Online ISBN: 978-3-540-69158-7
eBook Packages: Computer ScienceComputer Science (R0)