Toyoshi Torioka

Learn More
It has been claimed that pattern separation in cerebellar cortex plays an important role in controlling movements and balance for vertebrates. A number of the neural models for cerebellar cortex have been proposed and their pattern separability has been analyzed. These results, however, only explain a part of pattern separability in random neural nets. The(More)
A new mapping network combined wavelet and neural networks is proposed. The algorithm consists of two process: the self-construction of networks and the minimization of errors. In the first process, the network structure is determined by using wavelet analysis. In the second process, the approximation errors are minimized. The merits of the proposed network(More)
A two-layer random neural net with inhibitory connections composing of threshold elements has been regarded as a model of the cerebellar cortex. Many properties of pattern separation with the model have been disclosed through consideration on the degree of pattern separation. However, we have not shown yet that the degree of pattern separation is given by(More)
A new method to design wavelet networks using genetic algorithms is proposed. Designing wavelet networks is regarded as a combinatorial optimization problem to arrange the windows of wavelets and then genetic algorithms are used to derive their optimal arrangement. The effectiveness of the proposed method is verified through computer experiments.
The two-layered random neural network with the feedforward inhibitory connections has the interesting property that the input patterns with the same firing rate are separated uniformly under a certain condition, independently of the overlapping rate of the patterns. This paper gives the general condition for the uniform separation of the input patterns with(More)