Abstract
The neocognitron is a hierarchical, multi-layered neural network capable of robust visual pattern recognition. The neocognitron acquires the ability to recognize visual patterns through learning. The winner-kill-loser is a recently introduced competitive learning rule that has been shown to improve the neocognitron’s performance in character recognition. This paper proposes an improved winner-kill-loser rule, in which we use a triple threshold, instead of the dual threshold used as part of the conventional winner-kill-loser. It is shown theoretically, and also by computer simulation, that the use of a triple threshold makes the learning process more stable. In particular, a high recognition rate can be obtained with a smaller network.
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.: Neocognitron trained with winner-kill-loser rule. Neural Networks 23(7), 926–938 (2010)
Fukushima, K.: Neocognitron for handwritten digit recognition. Neurocomputing 51, 161–180 (2003)
Fukushima, K.: Increasing robustness against background noise: visual pattern recognition by a neocognitron. Neural Networks 24(7), 767–778 (2011)
ETL1 database, http://www.is.aist.go.jp/etlcdb/#English
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fukushima, K., Hayashi, I., Léveillé, J. (2011). Neocognitron Trained by Winner-Kill-Loser with Triple Threshold. In: Lu, BL., Zhang, L., Kwok, J. (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7063. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24958-7_73
Download citation
DOI: https://doi.org/10.1007/978-3-642-24958-7_73
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24957-0
Online ISBN: 978-3-642-24958-7
eBook Packages: Computer ScienceComputer Science (R0)