Neocognitron for handwritten digit recognition

Neurocomputing

Volumn 51, Issue , 2003, Pages 161-180

  Fukushima, Kunihiko ^a  

^a TOKYO UNIVERSITY OF TECHNOLOGY   (Japan)

Author keywords

Handwritten digit; Multi layered network; Neocognitron; Neural network model; Visual pattern recognition

Indexed keywords

CHARACTER RECOGNITION; NEURAL NETWORKS;

DIGIT RECOGNITION; NEOCOGNITRON;

NEUROLOGY;

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION; CONTROLLED STUDY; DATA BASE; HANDWRITING; IMAGE ANALYSIS; IMAGE PROCESSING; LEARNING; MATHEMATICAL MODEL; PATTERN RECOGNITION; PRIORITY JOURNAL; TRAINING; VISION;

EID: 0037381347     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(02)00614-8     Document Type: Article

References (27)

1. E. Barnard, D. Casasent, Shift invariance and the neocognitron, Neural Networks 3 (4) (1990) 403-410.
2. M.C.M. Elliffe, E.T. Rolls, S.M. Stringer, Invariant recognition of feature combinations in the visual system, Biol. Cybernet. 86 (2002) 59-71.
3. ETL1 database: http://www.etl.go.jp/~etlcdb/index.htm.
4. K. Fukushima, Neocognitron: a hierarchical neural network capable of visual pattern recognition, Neural Networks 1 (2) (1988) 119-130.
5. K. Fukushima, S. Miyake, Neocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position, Pattern Recognition 15 (6) (1982) 455-469.
6. K. Fukushima, K. Nagahara, H. Shouno, Training neocognitron to recognize handwritten digits in the real world, pAs'97 (2nd Aizu International Symposium on Parallel Algorithms/Architectures Synthesis), IEEE Computer Society Press, Silver Spring, MD, 1997, pp. 292-298.
7. K. Fukushima, M. Tanigawa, Use of different thresholds in learning and recognition, Neurocomputing 11 (1) (1996) 1-17.
8. K. Fukushima, N. Wake, Improved neocognitron with bend-detecting cells, IJCNN'92, Vol. IV, Baltimore, MD, USA, 1992, pp. 190-195.
9. R.M. Gray, Vector quantization, IEEE Trans. Acoust. Speech Signal Process. Mag. 1 (2) (1984) 4-29.
10. T.H. Hildebrandt, Optimal training of thresholded linear correlation classifiers, IEEE Trans. Neural Networks 2 (6) (1991) 577-588.
11. G.S. Himes, R.M. Iñigo, Automatic target recognition using a neocognitron, IEEE Trans. Knowledge Data Eng. 4 (2) (1992) 167-172.
12. D.H. Hubel, T.N. Wiesel, Receptive fields, binocular interaction and functional architecture in the cat's visual cortex, J. Physiol. (London) 106 (1) (1962) 106-154.
13. D.H. Hubel, T.N. Wiesel, Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat, J. Neurophysiol. 28 (2) (1965) 229-289.
14. E.J. Kim, Y. Lee, Handwritten hangul recognition using a modified neocognitron, Neural Networks 4 (6) (1991) 743-750.
15. T. Kohonen, The self-organizing map, Proc. IEEE 78 (9) (1990) 1464-1480.
16. Y. LeCun, B. Boser, J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard, L.J. Jackel, Backpropagation applied to handwritten zip code recognition, Neural Comput. 1 (1989) 541-551.
17. S.B. Lo, H. Chan, J. Lin, H. Li, M.T. Freedman, S.K. Mun, Artificial convolution neural network for medical image pattern recognition, Neural Networks 8 (7/8) (1995) 1201-1214.
18. M.M. Menon, K.G. Heinemann, Classification of patterns using a self-organizing neural network, Neural Networks 1 (3) (1988) 201-215.
19. C. Neubauer, Evaluation of convolutional neural networks for visual recognition, IEEE Trans. Neural Networks 9 (4) (1998) 685-696.
20. A. van Ooyan, B. Nienhuis, Pattern recognition in the neocognitron is improved by neuronal adaptation, Biol. Cybernet. 70 (1) (1993) 47-53.
21. S. Sato, J. Kuroiwa, H. Aso, S. Miyake, Recognition of rotated patterns using a neocognitron, in: L.C. Jain, B. Lazzerini (Eds.), Knowledge Based Intelligent Techniques in Character Recognition, CRC Press, Boca Raton, FL, 1999, pp. 49-64.
22. D. Shi, C. Dong, D.S. Yeung, Neocognitron's parameter tuning by genetic algorithms, Internat. J. Neural Systems 9 (6) (1999) 495-509.
23. C.H. Ting, Magnocellular pathway for rotation invariant neocognitron, Internat. J. Neural Systems 4 (1) (1993) 43-54.
24. C. Ting, K. Chuang, An adaptive algorithm for neocognitron to recognize analog images, Neural Networks 6 (2) (1993) 285-299.
25. D.S. Yeung, H. Chan, A hybrid cognitive system using production rules to synthesize neocognitrons, Internat. J. Neural Systems 5 (4) (1994) 345-355.
26. D.S. Yeung, H.S. Fong, A knowledge matrix representation for a rule-mapped neural network, Neurocomputing 7 (2) (1995) 123-144.
27. B.A. White, M.I. Elmasry, The digi-neocognitron: a digital neocognitron neural network model for VLSI, IEEE Trans. Neural Networks 3 (1) (1992) 73-85.