Title:
【発明の名称】自己組織型パタ-ン分類システム及び分類方法
Document Type and Number:
Japanese Patent JP3088171
Kind Code:
B2
Abstract:
A neural network includes a plurality of input nodes for receiving the respective elements of the input vector. A copy of all of the elements of the input vector is sent to the next level of nodes in the neural network denoted as intermediate nodes. The intermediate nodes each encode a separate template pattern. They compare the actual input pattern with the template and generate a signal indicative of the difference between the input pattern and the template pattern. Each of the templates encoded in the intermediate nodes has a class associated with it. The difference calculated by the intermediate nodes is passed to an output node for each of the intermediate nodes at a given class. The output node then selects the minimum difference amongst the values sent from the intermediate nodes. This lowest difference for the class represented by the output node is then forwarded to a selector. The selector receives such values from each of the output nodes of all of the classes and then selects that to output value which is a minimum difference. The selector in turn, generates a signal indicative of the class of the intermediate node that sent the smallest difference value.
Inventors:
Fumio Yoda
Application Number:
JP748992A
Publication Date:
September 18, 2000
Filing Date:
January 20, 1992
Export Citation:
Assignee:
Mitsubishi Electric Corporation
International Classes:
G06F15/18; G06G7/60; G06K9/66; G06N3/00; G06N3/04; G06N3/08; G06N99/00; (IPC1-7): G06F15/18; G06G7/60
Domestic Patent References:
| JP2125392A | ||||
| JP2127783A | ||||
| JP2211576A | ||||
| JP334079A | ||||
| JP3296880A |
Other References:
情報処理学会第４３回全国大会講演論文集ｐ２−１９９〜２−２００（平成３年１０月１９日〜２２日）依田文夫 外３名「複合ＬＶＱニューラルネットワークによる印刷漢字認識方式の検討」
情報処理学会第４３回全国大会講演論文集ｐ２−２０１〜２−２０２（平成３年１０月１９日〜２２日）川村秀男 外３名「ニューラルネットワークを用いた手書き数字認識」
情報処理学会第４３回全国大会講演論文集ｐ２−２０１〜２−２０２（平成３年１０月１９日〜２２日）川村秀男 外３名「ニューラルネットワークを用いた手書き数字認識」
Attorney, Agent or Firm:
Shoji Mizoi (2 outside)