東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Active labeling in deep learning and...

Wang, Dan.

FindBook

Google Book

Amazon

博客來

Active labeling in deep learning and its application to emotion prediction.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Active labeling in deep learning and its application to emotion prediction./
作者:	Wang, Dan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2013,
面頁冊數:	101 p.
附註:	Source: Dissertation Abstracts International, Volume: 78-03(E), Section: B.
Contained By:	Dissertation Abstracts International78-03B(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10180856
ISBN:	9781369295221

Active labeling in deep learning and its application to emotion prediction.
Wang, Dan.

Active labeling in deep learning and its application to emotion prediction. - Ann Arbor : ProQuest Dissertations & Theses, 2013 - 101 p.

Source: Dissertation Abstracts International, Volume: 78-03(E), Section: B.

Thesis (Ph.D.)--University of Missouri - Columbia, 2013.

Recent breakthroughs in deep learning have made possible the learning of deep layered hierarchical representations of sensory input. Stacked restricted Boltzmann machines (RBMs), also called deep belief networks (DBNs), and stacked autoencoders are two representative deep learning methods. The key idea is greedy layer-wise unsupervised pre-training followed by supervised fine-tuning, which can be done efficiently and overcomes the difficulty of local minima when training all layers of a deep neural network at once. Deep learning has been shown to achieve outstanding performance in a number of challenging real-world applications.

ISBN: 9781369295221Subjects--Topical Terms:

523869
Computer science.

Active labeling in deep learning and its application to emotion prediction.
LDR:04130nmm a2200313 4500 001 2121937
005 20170830070058.5
008 180830s2013 ||||||||||||||||| ||eng d
020 $a 9781369295221
035 $a (MiAaPQ)AAI10180856
035 $a AAI10180856
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Dan. $3 1275311
245 1 0 $a Active labeling in deep learning and its application to emotion prediction.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2013
300 $a 101 p.
500 $a Source: Dissertation Abstracts International, Volume: 78-03(E), Section: B.
500 $a Adviser: Yi Shang.
502 $a Thesis (Ph.D.)--University of Missouri - Columbia, 2013.
520 $a Recent breakthroughs in deep learning have made possible the learning of deep layered hierarchical representations of sensory input. Stacked restricted Boltzmann machines (RBMs), also called deep belief networks (DBNs), and stacked autoencoders are two representative deep learning methods. The key idea is greedy layer-wise unsupervised pre-training followed by supervised fine-tuning, which can be done efficiently and overcomes the difficulty of local minima when training all layers of a deep neural network at once. Deep learning has been shown to achieve outstanding performance in a number of challenging real-world applications.
520 $a Existing deep learning methods involve a large number of meta-parameters, such as the number of hidden layers, the number of hidden nodes, the sparsity target, the initial values of weights, the type of units, the learning rate, etc. Existing applications usually do not explain why the decisions were made and how changes would affect performance. Thus, it is difficult for a novice user to make good decisions for a new application in order to achieve good performance. In addition, most of the existing works are done on simple and clean datasets and assume a fixed set of labeled data, which is not necessarily true for real-world applications.
520 $a The main objectives of this dissertation are to investigate the optimal metaparameters of deep learning networks as well as the effects of various data pre-processing techniques, propose a new active labeling framework for cost-effective selection of labeled data, and apply deep learning to a real-world application -- emotion prediction via physiological sensor data, based on real-world, complex, noisy, and heterogeneous sensor.
520 $a data. For meta-parameters and data pre-processing techniques, this study uses the benchmark MNIST digit recognition image dataset and a sleep-stage-recognition sensor dataset and empirically compares the deep network's performance with a number of different meta-parameters and decisions, including raw data vs. pre-processed data by Principal Component Analysis (PCA) with or without whitening, various structures in terms of the number of layers and the number of nodes in each layer, stacked RBMs vs. stacked autoencoders. For active labeling, a new framework for both stacked RBMs and stacked autoencoders is proposed based on three metrics: least confidence, margin sampling, and entropy. On the MINIST dataset, the methods outperform random labeling consistently by a significant margin. On the other hand, the proposed active labeling methods perform similarly to random labeling on the sleep-stage-recognition dataset due to the noisiness and inconsistency in the data. For the application of deep learning to emotion prediction via physiological sensor data, a software pipeline has been developed. The system first extracts features from the raw data of four channels in an unsupervised fashion and then builds three classifiers to classify the levels of arousal, valence, and liking based on the learned features. The classification accuracy is 0.609, 0.512, and 0.684, respectively, which is comparable with existing methods based on expert designed features.
590 $a School code: 0133.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a University of Missouri - Columbia. $3 1017522
773 0 $t Dissertation Abstracts International $g 78-03B(E).
790 $a 0133
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10180856