Ricoh Company, Ltd.

Satoshi Otsuki

Takahiro Watanabe

Toshiyuki Furuta

Sugitaka Oteki

Hirotoshi Eguchi

Hiroyuki Horiguchi

Toshihiro Tsukagoshi

Shuji Motomura

Atsuo Hashimoto

Eiki Aono

Yutaka Ebi

Yoshio Watanabe

Takashi Kitaguchi

Tatsuya Furukawa

An input value sorter for calculating a conformity grade in a fuzzy inferential device has a comparator for sequentially receiving data indicative of a position of each of vertexes of a membership function defined as a polygon and receiving fact data. The comparator sequentially compares the fact data showing a determined value with the data indicative of the position of each of the vertexes. The input value sorter also has a device for specifying a side or vertex of the polygon belonging to the fact data on the basis of compared results of the comparator and an input order of the vertexes. A grade arithmetic unit has this input value sorter. In this grade arithmetic unit, the membership function can be suitably sorted by a simplified construction.

Grade arithmetic unit and input value sorter used therein

The present invention calculates an error between an output expected value with respect to an input of fuzzy inference and an output result of fuzzy inference using a singleton as the conclusion-membership function, calculates the distance proportional to the ratio of the degrees of contribution of each conclusion-membership functions in the defuzzy calculation for fuzzy inference, and uses the error and the distance as the basis to update tuning of the conclusion-membership function.

Membership function tuning system using defuzzy calculation

A neuron unit processes a plurality of input signals and for outputs an output signal which is indicative of a result of the processing, and includes input lines for receiving the input signals, a forward process part including a supplying part for supplying weight functions and an operation part for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal, and a self-learning part including a function generating part for generating new weight functions based on errors between the output signal of the forward process part and teaching signals and a varying part for varying the weight functions supplied by the supplying part of the forward process part to the new weight functions generated by the generating part. The supplying part includes a memory for storing each weight function in the form of a binary value, and a generating circuit for generating a random pulse train based on each binary value stored in the memory. The random pulse train describes each weight function in the form of a pulse signal having a pulse density.

Neuron unit

A neuron unit processes a plurality of binary input signals and outputs a neuron output signal which is indicative of a result of the processing. The neuron unit is provided with a plurality of first gates respectively for carrying out a logical operation on a binary input signal and a weighting coefficient, a second gate for carrying out a logical operation on an excitatory output signal of each of the first gates, a third gate for carrying out a logic operation on an inhibitory output signal of each of the first gates, a fourth gate for synthesizing output signals of the second and third gates and outputting the neuron output signal, and a generating circuit for generating the weighting coefficients which are supplied to each of the first gates. The generating circuit for generating one weighting coefficient includes a random number generator for generating random numbers, and a comparator for comparing each random number r with a predetermined value q and for outputting a pulse signal having first and second values depending on whether each random number r is such that r.ltoreq.q or r&gt;q, and each weighting coefficient is described by a pulse density.

Neuron unit and neuron unit network

Growing community of inventors

Ikeda, Japan

Satoshi Otsuki