【摘要】：針對(duì)傳統(tǒng)文本分類(lèi)算法準(zhǔn)確率低和正確率分布不均勻的問(wèn)題,提出了基于深度學(xué)習(xí)的文本分類(lèi)算法。深度信念網(wǎng)絡(luò)具有強(qiáng)大的學(xué)習(xí)能力,可以從高維的原始特征中提取高度可區(qū)分的低維特征,不僅能夠更全面的考慮到文本信息量,而且能夠進(jìn)行快速分類(lèi)。采用TF-IDF方法計(jì)算文本特征值,利用深度信念網(wǎng)絡(luò)構(gòu)造分類(lèi)器進(jìn)行精準(zhǔn)分類(lèi)。實(shí)驗(yàn)結(jié)果表明,與支持向量機(jī)、神經(jīng)網(wǎng)絡(luò)和極端學(xué)習(xí)機(jī)等常用分類(lèi)算法相比,該算法有更高的準(zhǔn)確率和實(shí)用性,為文本的分類(lèi)研究開(kāi)拓了新思路。
[Abstract]:Aiming at the problems of low accuracy and uneven distribution of correct rate in traditional text classification algorithms, a text classification algorithm based on depth learning is proposed. Deep belief network has a strong learning ability, it can extract highly distinguishable low-dimensional features from high-dimensional original features, which can not only take into account the amount of text information more comprehensively, but also can be classified quickly. The TF-IDF method is used to calculate the text eigenvalues and the depth belief network is used to construct a classifier for accurate classification. The experimental results show that this algorithm has higher accuracy and practicability than other common classification algorithms such as support vector machine, neural network and extreme learning machine, and opens up a new idea for text classification research.
【作者單位】： 東北林業(yè)大學(xué)信息與計(jì)算機(jī)工程學(xué)院;
【基金】：中央高�；究蒲袠I(yè)務(wù)費(fèi)專(zhuān)項(xiàng)資金(2572015DY07) 黑龍江省自然科學(xué)基金(F201347) 哈爾濱市科技創(chuàng)新人才專(zhuān)項(xiàng)資金(2013RFQXJ100) 國(guó)家自然科學(xué)基金(61300098) 教育部大學(xué)生創(chuàng)新訓(xùn)練計(jì)劃項(xiàng)目(201510225043)
【分類(lèi)號(hào)】：TP391.1

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鄭智捷;幻序合并分類(lèi)算法[J];計(jì)算機(jī)學(xué)報(bào);1984年05期

2 劉t，

本文編號(hào)：2342154