协同式神经网络的识别性能分析  

Analysis of the Recognition Performances of Synergetic Neural Network

作　　者：赵同[1] 戚飞虎[1] 冯炯[1] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200030

出　　处：《电子学报》2000年第1期74-77,共4页Acta Electronica Sinica

基　　金：国家自然科学基金!(NO.69772002)

摘　　要：本文对一类全新的神经网络──协同式神经网络的性能进行了研究．在介绍了模式识别协同式神经网络原理的基础上，进一步分析了离散协同网络的识别稳定性及识别率，并与传统神经网络──Ｈｏｐｆｉｅｌｄ网络在汉字图像识别方面进行了性能比较，进而指出协同式神经网络在真实汉字图像识别性能上具有极大的优势．The performance of synergetic neural network(SNN) is discussed. Based on the theory of SNN on Pattern recognition, the stability and recognition rate of discrete SNN are analyzed. We compare its performances with traditional neural network- Hopfield network in the application in real images recognition.At last,we point out that Synergetic neural network has great advantages in the recognition of the real Chinese character images.

关 键 词：协同式 神经网络 图像识别 识别性能 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]