Kabushiki Kaisha Toshiba

Hitachi, Ltd.

Kazuo Nishimura

Minoru Koizumi

Makoto Kayashima

Naotake Natori

Masato Terada

Takaaki Ogino

Kazunari Hirayama

Takahiko Kawashima

Tetsuya Fujiyama

In view of providing a network system enabling communication having passed fire walls (repeaters) and assuring high security and operation flexibility through access control based on users and applications, a user-held table indicating correspondence between repeaters and passwords, a repeater-held table indicating correspondence between users and passwords and a table indicating access regions are defined respectively for users, departments of users and official positions of users and a route control information storing table indicating correspondence between networks and next transmitting destination is also provided to execute the access control for each user. Moreover, the repeater is provided with the repeating route control table so that a repeater located in the course of route to the transmitting destination computer and allowing communication from the transmitting side computer is selected from the data repeating control table and the process for requesting the repeating operation of communication with the destination is executed to the selected repeater.

Repeater and network system utililzing the same

Repeater and network system utilizing the same

A pattern recognition apparatus includes a pattern analyzer for analyzing a similarity between an input pattern and a learning pattern, a hypothetic pattern forming section for forming, as a hypothetic pattern, a predetermined pattern corresponding to the input pattern in accordance with an analysis result from the pattern analyzer, a comparator for comparing the hypothetic pattern formed by the hypothetic pattern forming section with the input pattern, an attribute descriptor in which a comparison result obtained by the comparator and the analysis result obtained by the pattern analyzer are described, and an inference section for, referring to a description described in the attribute descriptor, outputting a clear analysis result obtained from the pattern analyzer as a final recognition result, and starting the hypothetic pattern forming section in response to an ambiguous analysis result by the pattern analyzer.

Pattern recognition apparatus

A neural network computation apparatus having a plurality of layers, each of the plurality of layers has at least an input layer and an output layer, each layer having a plurality of units, a plurality of links, each of the plurality of links connecting units on the plurality of layers, and changing means for changing input and output characteristics of a particular unit of the plurality of units and/or the weight of a particular link of the plurality of links in accordance with an output of the output layer after learning an example and with a particular rule. After the neural network computation apparatus learns an example, the changing means changes input and output characteristics of units and weights of links in accordance with outputs of the output layer and a particular rule. Thus, a mutual operation between a logical knowledge and a pattern recognizing performance can be accomplished and thereby a determination close to that of a specialist can be accomplished. In other words, a proper determination in accordance with an experience can be made so as to deal with unknown patterns with high flexibility.

Neural network with modification of neuron weights and reaction

Growing community of inventors

Hadano, Japan

Kazuo Nishimura