Maiko Sato

Learn More
The nonlinear classiier is eeective for many practical problems. We have already proposed a method for constructing a nonlinear classiier using Legendre polynomials and have obtained good results on many actual data. In this approach, a set of original features is rst extended to a large number of new features in a nonlinear fashion and then some(More)
An ad-hoc network is composed only of terminals and can transmit information without infrastructure such as access points. And it transmit information from a source to a destination via multiple hops. However, in an ad-hoc network, the network topology always changes since the terminals may move freely. Therefore the path search from a source to a(More)
In our previous research, the Maximum-Flow Neural Network (MF-NN) was proposed, and we showed that the MF-NN is possible to solve any maximum-flow problems. However, the MF-NN has problems of convergence of sigmoidal function. In this research, we propose novel MF-NN using piecewise linear function for improving those problems. Moreover, this novel method(More)
In this paper, we propose a novel path searching method based on the local winner take all (WTA) circuits that are constructed by corporative and competitive networks to find the maximum local current on each node connected to nonlinear resistance. By putting nonlinear resistances on the network, the network has a saturation characteristic of current. Each(More)
  • 1