電機資訊學院: 資訊工程學研究所指導教授: 徐宏民白聖顗Bai, Sheng-YiSheng-YiBai2017-03-032018-07-052017-03-032018-07-052016http://ntur.lib.ntu.edu.tw//handle/246246/275562近期,深度學習依賴大量的標記資料取得相當驚人的成果。 讓人不禁想到網路上資料量的豐富是否可以妥善利用,然而那些資料大多沒有標記的。 因此,使用極有限的標記實例進行監督式學習,並將其推廣到廣大的未標記資料,以改善泛化性能是重要的。 在這份論文中,我們重新審視基於圖的半監督學習演算法,並提出了更適合深度卷積神經網絡的線上圖之構建法。 我們提出了在深度神經網絡半監督學習上的類EM演算法:正向傳遞時,圖是基於當下網絡的輸出構成,圖將用於損失計算,在反向傳遞時用來幫助更新網絡狀態。 我們證明我們的在線方法會比傳統靜態(離線)的方法來的具有優勢,靜態方法的缺點在於資料「表示」是不變的,並不具有學習效果。The recent promising achievements of deep learning rely on the large amount of labeled data. Considering the abundance of data on the web, most of them do not have labels at all. Therefore, it is important to improve generalization performance using unlabeled data on supervised tasks with few labeled instances. In this work, we revisit graph-based semi-supervised learning algorithms and propose an online graph construction technique which suits deep convolutional neural network better. We consider an EM-like algorithm for semi-supervised learning on deep neural networks: In forward pass, the graph is constructed based on the network output, and the graph is then used for loss calculation to help update the network by back propagation in the backward pass. We demonstrate the strength of our online approach compared to the conventional ones whose graph is constructed on static but not robust enough feature representations beforehand.論文使用權限: 不同意授權卷積神經網絡半監督式學習線上圖之建構Convolutional Neural NetworksSemi-Supervised LearningOnline Graph Construction藉由圖之線上構建於卷積神經網絡上進行半監督式學習Semi-supervised Learning for Convolutional Neural Networks via Online Graph Constructionthesis