While in the stage of document classifying, NNTCS inputs feature vectors of the document to be classified, runs network with fixed weights, then compares the output with the predefined threshold to judge the class of the unlabelled document.

• 而在文本分类的时候，输入待分类文档的特征向量，运行固定权值的网络，得到的输出值与阈值比较确定类别。