The neocognitron is a hierarchical, multilayered artificial neural network proposed by Kunihiko Fukushima in 1979.[1] It has been used for Japanese handwritten character recognition and other pattern recognition tasks, and served as the inspiration for convolutional neural networks.[2]
The neocognitron was inspired by the model proposed by Hubel & Wiesel in 1959. They found two types of cells in the visual primary cortex called simple cell and complex cell, and also proposed a cascading model of these two types of cells for use in pattern recognition tasks.[3][4]
The neocognitron is a natural extension of these cascading models. The neocognitron consists of multiple types of cells, the most important of which are called S-cells and C-cells.[5] The local features are extracted by S-cells, and these features' deformation, such as local shifts, are tolerated by C-cells. Local features in the input are integrated gradually and classified in the higher layers.[6] The idea of local feature integration is found in several other models, such as the Convolutional Neural Network model, the SIFT method, and the HoG method.
There are various kinds of neocognitron.[7] For example, some types of neocognitron can detect multiple patterns in the same input by using backward signals to achieve selective attention.[8]
YouTube Encyclopedic
-
1/3Views:1 1071 230 6701 224 879
-
11-785 Spring 23 Lecture 10: Models of vision, Convolutional Neural Networks
-
Convolutional Neural Networks (CNNs) explained
-
Deep Learning | What is Deep Learning? | Deep Learning Tutorial For Beginners | 2023 | Simplilearn
Transcription
See also
- Artificial neural network
- Deep learning
- Pattern recognition
- Receptive field
- Self-organizing map
- Unsupervised learning
Notes
- ^ Fukushima, Kunihiko (October 1979). "位置ずれに影響されないパターン認識機構の神経回路のモデル --- ネオコグニトロン ---" [Neural network model for a mechanism of pattern recognition unaffected by shift in position — Neocognitron —]. Trans. IECE (in Japanese). J62-A (10): 658–665.
- ^ LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey (2015). "Deep learning" (PDF). Nature. 521 (7553): 436–444. Bibcode:2015Natur.521..436L. doi:10.1038/nature14539. PMID 26017442. S2CID 3074096.
- ^ David H. Hubel and Torsten N. Wiesel (2005). Brain and visual perception: the story of a 25-year collaboration. Oxford University Press US. p. 106. ISBN 978-0-19-517618-6.
- ^ Hubel, DH; Wiesel, TN (October 1959). "Receptive fields of single neurones in the cat's striate cortex". J. Physiol. 148 (3): 574–91. doi:10.1113/jphysiol.1959.sp006308. PMC 1363130. PMID 14403679.
- ^ Fukushima 1987, p. 83.
- ^ Fukushima 1987, p. 84.
- ^ Fukushima 2007.
- ^ Fukushima 1987, pp. 81, 85.
References
- Fukushima, Kunihiko (April 1980). "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position". Biological Cybernetics. 36 (4): 193–202. doi:10.1007/bf00344251. PMID 7370364. S2CID 206775608.
- Fukushima, Kunihiko; Miyake, S.; Ito, T. (1983). "Neocognitron: a neural network model for a mechanism of visual pattern recognition". IEEE Transactions on Systems, Man, and Cybernetics. SMC-13 (3): 826–834. doi:10.1109/TSMC.1983.6313076. S2CID 8235461.
- Fukushima, Kunihiko (1987). "A hierarchical neural network model for selective attention". In Eckmiller, R.; Von der Malsburg, C. (eds.). Neural computers. Springer-Verlag. pp. 81–90.
- Fukushima, Kunihiko (2007). "Neocognitron". Scholarpedia. 2 (1): 1717. Bibcode:2007SchpJ...2.1717F. doi:10.4249/scholarpedia.1717.
- Hubel, D.H.; Wiesel, T.N. (1959). "Receptive fields of single noreones in the cat's striate cortex". J Physiol. 148 (3): 574–591. doi:10.1113/jphysiol.1959.sp006308. PMC 1363130. PMID 14403679.
External links
- Neocognitron on Scholarpedia
- NeoCognitron by Ing. Gabriel Minarik - application (C#) and video
- Neocognitron resources at Visiome Platform - includes MATLAB environment
- Beholder - a Neocognitron simulator
 | This artificial intelligence-related article is a stub. You can help Wikipedia by expanding it. |
This page was last edited on 4 May 2024, at 02:15