A local connected neural oscillator network for pattern segmentation
This paper proposes the local connected neural oscillator network which is useful for image processing. In this proposed network, each neural oscillator employs a learning method to control its phase and frequency. Since the learning method has an ability to control the phase adjustment of each neural oscillator, the information expression in the phase space is achievable. Furthermore, it is considered that the network has the ability to achieve real time image processing and information processing in a time series. The learning method is possible under the assumption that synapses have plasticity. However, since it is supposed that only the feedback synapse has plasticity, we can construct a network with high simplicity.
Unable to display preview. Download preview PDF.
- 1.Shun-ichi Amari, “Random Nets Consisting of Excitatory and Inhibitory Neuron-like Elements” IEICE Transactions vol.55-D pp. 179–185 (1972), (in Japanese)Google Scholar
- 2.Shun-ichi Amari, “Characteristics of Random Nets of Analog Neuron-Like Elements”, IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-2, no.5 pp. 643–657 (1972)Google Scholar
- 3.DeLiang Wang, “Emergent Synchrony in Locally Coupled Neural Oscillators”, IEEE Transactions on Neural Networks, vol.6, no.4 pp. 941–948 (1995)Google Scholar
- 4.Ch. von der Malsburg and W. Schneider, “A Neural Cocktail-Party Processor”, Biol. Cybern., vol.54, pp. 29–40 (1986)Google Scholar
- 5.Ch. von der Malsburg and Joachim Buhmann, “Sensory segmentation with coupled neural oscillators”, Biol. Cybern., vol.67, pp. 233–242 (1992)Google Scholar
- 6.Kenji Doya and Shuji Yoshizawa, “Motor Pattern Memory in Neural Network” IEICE technical report MBE87-141(1987), (in Japanese)Google Scholar
- 7.Hiroaki Kurokawa and Shinsaku Mori,“A Learning method for the Synchronization of the Oscillatory Neural Network” (submitted to 1996 World Congress on Neural Networks)Google Scholar
- 8.R.Hecht Nielsen,“Neurocomputing”, Addison Wesley (1990)Google Scholar
- 9.Hirofumi Nagashino and Yohsuke Kinouchi, “An Oscillatory Input Makes a Neural Network Nonoscillatory”, Proc. of International Symposium on Nonlinear Theory and Its Application (NOLTA'95), pp.1137–1140Google Scholar