公开(公告)号：US07016885B1

公开(公告)日：2006-03-21

申请号：US10230425

申请日：2002-08-28

申请人： Wasfy B. Mikhael ,  Manal M. Abdelwahab ,  Venkatesh Krishnan

发明人： Wasfy B. Mikhael ,  Manal M. Abdelwahab ,  Venkatesh Krishnan

IPC分类号： G06N3/02 ,  G06T1/40

CPC分类号： G06N3/0454 ,  G06K9/52 ,  G06K9/629 ,  G06N3/086

摘要： A Self-Designing Intelligent Signal Processing System Capable of Evolutional Learning for Classification/Recognition of One and Multidimensional Signals is described which classifies data by an evolutionary learning environment that develops the features and algorithms that are best suited for the recognition problem under consideration. The System adaptively learns what data need to be extracted in order to recognize the given pattern with the least amount of processing. The System decides what features need to be selected for classification and/or recognition to fit a certain structure that leads to the least amount of processing according to the nature of the given data. The System disclosed herein is capable of recognizing an enormously large number of patterns with a high accuracy.

摘要翻译： 描述了一种能够进行一维和多维信号分类/识别的卷积学习的自设计智能信号处理系统，其通过进化学习环境对数据进行分类，该环境开发出最适合于考虑的识别问题的特征和算法。 系统自适应地学习需要提取哪些数据，以便以最少的处理量来识别给定的模式。 系统决定为了分类和/或识别而需要选择什么特征以适应根据给定数据的性质导致最少处理量的特定结构。 本文公开的系统能够以高精度识别大量的图案。