公开(公告)号：US20130117207A1

公开(公告)日：2013-05-09

申请号：US13626244

申请日：2012-09-25

Applicant: Youn-ho Kim ,  Chang-mok Choi ,  Kun-soo Shin ,  Myoung-ho Lee ,  Jin-kwon Kim

Inventor： Youn-ho Kim ,  Chang-mok Choi ,  Kun-soo Shin ,  Myoung-ho Lee ,  Jin-kwon Kim

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method of classifying an input pattern and a pattern classification apparatus are provided. The method includes enabling an artificial neural network to learn based on learning input data received by an input layer of the artificial neural network, determining classification of an input pattern received by the input layer of the enabled artificial neural network according to an output value obtained from an output layer of the artificial neural network, the obtained output value being based on the input pattern, updating connection intensities of a plurality of connection lines of the enabled artificial neural network to output a result value indicating the determined classification from the output layer when the input pattern, and determining updated classification of the input pattern according to an updated output value obtained from an output layer of the updated artificial neural network, the obtained updated output value being based on the input pattern.

Abstract translation: 提供了对输入图案进行分类的方法和图案分类装置。 该方法包括使得人造神经网络能够基于由人造神经网络的输入层接收的学习输入数据来学习，根据从人造神经网络的输入层获得的输出值来确定由使能的人造神经网络的输入层接收的输入模式的分类 所述人造神经网络的输出层，所获得的输出值基于所述输入图案，更新所述使能人造神经网络的多条连接线的连接强度，以在所述输入层输出由所述输入层输出所述确定的分类的结果值时，从所述输出层输出 输入图案，并且根据从更新的人造神经网络的输出层获得的更新的输出值来确定输入模式的更新分类，所获得的更新输出值基于输入模式。