结合概率型神经网络(PNN)和学习矢量量化(LVQ)算法的文本分类方法

针对文本自动分类问题,提出一种基于概率型神经网络(PNN)和学习矢量量化(LVQ)相结合的文本分类算法,该方法借助TFIDF方法提取文本特征及特征值,形成文本分类特征向量,利用概率型神经网络构建分类模型,并利用LVQ学习算法对神经网络模型竞争层网络进行学习,使相应模式向量相互靠拢,远离其他模式,从而实现文本分类.实验结果表明,提出的该方法在文本分类中表现了很好的效果,不仅具有很好的分类准确率,还表现出很好的学习效率.

Text Classification Combined with Probabilistic Neural Network (PNN) and Learning Vector Quantization (LVQ) Algorithm

Aiming at the problem of text classification, one text classification method based on the probabilistic neural network （ PNN ） and learning vector quantization （ LVQ ） is proposed. The text features and feature values are extracted by use of TFIDF method, and text categorization feature vector are formed. In addition, classification model based on prohabilistic neural network can be constructed and the learning of competitive layer network is completed by using LVQ algorithms, so the corresponding pattern vector to move closer to each other, away from the other modes, thereby realizing text classification. The experimental results show that the method in the text classification performance with very good results, and not only has good classification accuracy, but also shows a good learning efficiency.