Showing papers in "IEICE technical report. Nonlinear problems in 2001"
Journal Article•
TL;DR: A simple and effective model to realize bursting phenomena in Amari‐Hopfield coupled neurons is proposed, and this model can constructively design desirable bursting responses.
Abstract: To clarify the mechanism of the information processing in the brain of living organisms, and investigate information coding of a neuron, a reasonable mathematical model of a neuron is needed. Various models have been proposed and analyzed for now, some relationship between bursting response and bifurcations. In this paper, we propose a simple and effective model to realize bursting phenomena in Amari-Hopfield coupled neurons. In this model, we can constructively design desirable bursting responses. Bifurcation diagrams and some analytical results are given, and a basic design scheme to generate a bursting is shown. © 2003 Wiley Periodicals, Inc. Electr Eng Jpn, 146(2): 43–53, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.10217
6 citations
Journal Article•
1 citations
Journal Article•
TL;DR: A data-dependent α-trimmed mean filter using backpropagation networks is proposed, and by processing taking into account the edge portions, both edge preservation and mixed noise elimination are attained simultaneously.
Abstract: Elimination of mixed noise consisting of white Gaussian noise and impulsive noise is one of the important problems in image processing. In this paper, a data-dependent α-trimmed mean filter using backpropagation networks is proposed. In order to determine an appropriate value of α for each processing point, the pattern classification capability of the backpropagation networks is used. Further, by processing taking into account the edge portions, both edge preservation and mixed noise elimination are attained simultaneously. Finally, the effectiveness of the proposed method is verified by simulation. © 2003 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 86(7): 30–40, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjc.10061
Journal Article•
TL;DR: The neural networks having the time-variant connection system is proposed to find the solution quickly without the influence of local minima for multi-layer channel routing problem.
Abstract: It is necessary for designing VLSI to arrange wirings not to overlap each other in the wiring area of a layer. The problem to find such arrangement is called multi-layer channel routing problem. This article proposes the neural networks having the time-variant connection for such problem. In previous studies, a monotonously decreasing energy function is introduced into the system. Therefore, the system operates toward the minimum of the energy. Then, to find the optimum solution, this minimum corresponds to the minimum of the cost function. However, this method hardly finds the optimum solution if the energy function has many local minima. On the other hand, higher order connection system is scarcely influenced by local minima to find the solution. It takes, however, the system so long time to find the solution. Then, in this article, the time-variant connection system is proposed to find the solution quickly without the influence of local minima.
Journal Article•