计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2014年
9期
176-181,270
,共7页
卷积神经网络%k-均值聚类%碎纸片拼接%卷积自动编码器%深度学习
捲積神經網絡%k-均值聚類%碎紙片拼接%捲積自動編碼器%深度學習
권적신경망락%k-균치취류%쇄지편병접%권적자동편마기%심도학습
convolutional neural networks%k-means clustering%stitching of scrapped paper%convolutional auto-encoder%deep learning
近年来，深度卷积网络在图像识别、语音识别和自然语言处理等领域广泛使用，取得了很好的效果。为解决全部样本均为无标签数据的分类问题，对深度卷积神经网络进行了改进，采用卷积自动编码器学习输入样本的特征，用k-均值聚类器代替深度卷积网络中的分类器，建立了改进的深度卷积网络结构，给出了相应的学习算法，将其用于解决碎纸片拼接问题。实验表明，该方法有效可行，提高了碎纸片拼接的准确性和鲁棒性。
近年來，深度捲積網絡在圖像識彆、語音識彆和自然語言處理等領域廣汎使用，取得瞭很好的效果。為解決全部樣本均為無標籤數據的分類問題，對深度捲積神經網絡進行瞭改進，採用捲積自動編碼器學習輸入樣本的特徵，用k-均值聚類器代替深度捲積網絡中的分類器，建立瞭改進的深度捲積網絡結構，給齣瞭相應的學習算法，將其用于解決碎紙片拼接問題。實驗錶明，該方法有效可行，提高瞭碎紙片拼接的準確性和魯棒性。
근년래，심도권적망락재도상식별、어음식별화자연어언처리등영역엄범사용，취득료흔호적효과。위해결전부양본균위무표첨수거적분류문제，대심도권적신경망락진행료개진，채용권적자동편마기학습수입양본적특정，용k-균치취류기대체심도권적망락중적분류기，건립료개진적심도권적망락결구，급출료상응적학습산법，장기용우해결쇄지편병접문제。실험표명，해방법유효가행，제고료쇄지편병접적준학성화로봉성。
In recent years, deep convolutional networks are widely used in image recognition, speech recognition and natural language processing and other fields, which have achieved very good results. In this paper, in order to solve classification problems with all the samples being unlabeled data, deep convolutional neural network is improved and the corresponding learning algorithm is given,with the k-means clustering device replacing the classifier in deep convolutional network and adopting convolutional auto-encoder. The improved learning algorithm is used to solve the stitching of scrapped paper. The experiments show that, this method is effective and feasible, which improves the accuracy and robustness of the stitching of scrapped paper.
