BP模式识别与Hopfield联想记忆识别能力的比较

神经网络可以进行模式识别,这一功能具有很高的实用价值.主要研究BP神经网络和离散Hopfield神经网络的识别能力.BP网络是前向神经网络,使用的是监督式学习规则.离散Hopfield是一种反馈网络,结构上输入、输出节点相连使得网络系统的输出状态具有动态变化特性.就数字,字母,手写体数字比较了BP网络和离散Hopfield网络的识别能力,得到了可观的结论,对两个网络的应用做更进一步的阐述.

The Comparison of BP Pattern Recognition Ability and Hopfield Associative Memory Recognition Ability

Neural network can be used in pattern recognition.This function has great utility value.This paper studies the recognition ability of BP network and the discrete Hopfield neural network.BP network is a feed-forward neural network,using supervised learning rules Discrete Hopfield is a kind of feedback network,input and output of connected nodes makes the network system retain dynamic characteristic.This paper compares the identification ability of BP network and discrete Hopfield network in numbers,letters,handwritten digit,receiving the considerable conclusion,making further elaboration about the appUcation to the two networks.