This paper describes a self-learning ULR fuzzy controller using temporal back propagation. The ULR fuzzy controller is a multi-layer feed-forward network in which each node performs an unidirectional linear response (ULR) function (node function) on incoming weighted signals. In order to achieve a desired input-output mapping, the weight parameters are updated with a temporal back propagation such that the state variables can follow a given desired trajectory as closely as possible. The temporal back prop agation algorithm is used to train the ULR fuzzy controller to a variety of problems. We demonstrate the effectiveness of the self-learning ULR fuzzy controller by applying it to a benchmark problem in in telligent control-the inverted pendulum system. Experiments show a very good control performance and self-learning capability of the ULR fuzzy controllers.

No abstract

SUMMARYIn this paper, a model of the neuron based on the dendrite mechanism is proposed. The neuron model takes the form of a dendrite, and the interaction between synapses and so on, which are not considered by the conventional model, is taken into account. In this paper, the form of a dendrite is assumed to be arbitrary and interaction is assumed to exist among all synapses. That is, a superfluous synapse is formed, and is expressed in a logical network, then the equivalence between them is shown. The ripened dendrite is formed during learning by screening unnecessary dendrites, and strengthening and fixing the useful dendrites. The model proposed in this paper can correspond to the linearly unseparated problem, unlike the one-layer traditional neuron. Moreover, learning of this model suggests the form of the dendrites and the positions of the excitation and inhibition synapses. This may give some very useful suggestions for biologists. © 2001 Scripta Technica, Electron Comm Jpn Pt 3, 84(8): 1124, 2001

No abstract

No abstract

No abstract

No abstract

No abstract