Abstract
It is well known that information processing in the brain depends on neuron systems. Simple neuron systems are neural networks, and their learning methods have been studied. However, we believe that research on large-scale neural network systems is still incomplete. Here, we propose a learning method for millions of neurons as resources for a neuron computer. The method is a type of recurrent path-selection, so the neural network objective must have nesting structures. This method is executed at high speed. When information processing is executed by analogue signals, the accumulation of errors is a grave problem. We equipped a neural network with a digitizer and AD/DA (Analogue Digital) converters constructed of neurons. They retain all information signals and guarantee precision in complex operations. By using these techniques, we generated an image shifter constructed of 8.6 million neurons. We believe that there is the potential to design a neuron computer using this scheme.
Similar content being viewed by others
References
Iwai E (1984) The brain: mechanisms of learning and memory in monkey and man (in Japanese). Asakura, Tokyo
Nakano K et al. (1990) An introduction to neuro-computing (in Japanese). Corona, Tokyo
Rumelhart DE, McCleland JL, PDP Research Group (1986) Parallel distributed processing, MIT Press, Cambridge
Mukaicono M (1991) Fuzzy logic (in Japanese). Daily Industry News, Tokyo
Aoyama T, Ichikawa H (1991) Back-propagation algorithm restricted with some conditions (in Japanese). Information Processing Society of Japan, Sig. Notes 91-NA-37
Moya MM, Hush DR (1996) Network constraints and multiobjective optimization for one-class classification. Neural Networks 9:463–474
Aoyama T (1999) Large-scale multi-layer neural networks. Information Processing Society of Japan, Sig. Notes 99-HPC-76
Zhu H, Aoyama T, Yoshihara I (1999) Functional memories constructed of neural networks. Proceedings of the 14th Korea Automatic Control Conference, p. E-210-213
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the Fifth International Symposium on Artificial Life and Robotics, Oita, Japan, January 26–28, 2000
About this article
Cite this article
Zhu, H., Aoyama, T. & Yoshihara, I. Simulations of construction learning for neuron-computer resources. Artif Life Robotics 5, 148–151 (2001). https://doi.org/10.1007/BF02481461
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02481461