<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">

學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Author: search.filters.author.Chien, Jen-TzungSubject: search.filters.subject.Deep learning

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item type:Item,
    SUPPORTIVE ATTENTION IN END-TO-END MEMORY NETWORKS
    (2018-01-01)
    Chien, Jen-Tzung
    ;
    Lin, Ting-An
    ;
    電機工程學系
    ;
    Department of Electrical and Computer Engineering
    Attention over natural language aims to spotlight on the meaningful region with representative keywords which can extract desirable meanings to accomplish a task of interest. The attention parameter is a latent variable which was indirectly estimated by minimizing the classification loss. For the task of question answering (QA), the classification loss may not sufficiently reflect the target answer. This paper proposes a direct solution which attends the meaningful region by minimizing the reconstruction loss due to auxiliary or supporting data which are available in different scenarios. In particular, minimizing the classification and reconstruction losses are carried out under the end-to-end memory network so that the memory-augmented question answering is realized. Such a supportive attention is implemented as a sequence-tosequence model which reconstructs the supporting sentence to assure the translation invariance. The merit of this method is sufficiently demonstrated for sequential learning by using the bAbI QA and dialog tasks.
  • Thumbnail Image
    Item type:Item,
    MARKOV RECURRENT NEURAL NETWORKS
    (2018-01-01)
    Kuo, Che-Yu
    ;
    Chien, Jen-Tzung
    ;
    電機工程學系
    ;
    Department of Electrical and Computer Engineering
    Deep learning has achieved great success in many real-world applications. For speech and language processing, recurrent neural networks are learned to characterize sequential patterns and extract the temporal information based on dynamic states which are evolved through time and stored as an internal memory. Traditionally, simple transition function using input-to-hidden and hidden-to-hidden weights is insufficient. To strengthen the learning capability, it is crucial to explore the diversity of latent structure in sequential signals and learn the stochastic trajectory of signal transitions to improve sequential prediction. This paper proposes the stochastic modeling of transitions in deep sequential learning. Our idea is to enhance latent variable representation by discovering the Markov state transitions in sequential data based on a K-state long short-term memory (LSTM) model. Such a latent state machine is capable of learning the complicated latent semantics in highly structured and heterogeneous sequential data. Gumbel-softmax is introduced to implement stochastic learning procedure with discrete states. Experimental results on visual and text language modeling illustrate the merit of the proposed stochastic transitions in sequential prediction with limited amount of parameters.
  • Thumbnail Image
    Item type:Item,
    ADVERSARIAL DOMAIN SEPARATION AND ADAPTATION
    (2017-01-01)
    Tsai, Jen-Chieh
    ;
    Chien, Jen-Tzung
    ;
    電機工程學系
    ;
    Department of Electrical and Computer Engineering
    Traditional domain adaptation methods attempted to learn the shared representation for distribution matching between source domain and target domain where the individual information in both domains was not characterized. Such a solution suffers from the mixing problem of individual information with the shared features which considerably constrains the performance for domain adaptation. To relax this constraint, it is crucial to extract both shared information and individual information. This study captures both information via a new domain separation network where the shared features are extracted and purified via separate modeling of individual information in both domains. In particular, a hybrid adversarial learning is incorporated in a separation network as well as an adaptation network where the associated discriminators are jointly trained for domain separation and adaptation according to the minmax optimization over separation loss and domain discrepancy, respectively. Experiments on different tasks show the merit of using the proposed adversarial domain separation and adaptation.
  • Thumbnail Image
    Item type:Item,
    DEEP SEMI-SUPERVISED LEARNING FOR DOMAIN ADAPTATION
    (2015)
    Chen, Hung-Yu
    ;
    Chien, Jen-Tzung
    ;
    電機學院
    ;
    College of Electrical and Computer Engineering
    Domain adaptation aims to adapt a classifier from source domain to target domain through learning a good feature representation that allows knowledge to be shared and transferred across domains. Most of previous studies are restricted to extract features and train classifier separately under a shallow model structure. In this paper, we propose a semi-supervised domain adaptation method which co-trains the feature representation and pattern classification under deep neural network (DNN) framework. The labeling in target domain is not required. We treat the hidden layers in DNN as feature extraction and construct the output layer consisting of classification and regression. Our idea is to conduct the feature-based domain adaptation which jointly minimizes the divergence between the distributions from labeled and unlabeled data in both domains, the reconstruction errors due to an autoencoder, and the classification errors due to the labeled data in source domain. Experiments on image recognition and sentiment classification show the superiority of DNN co-training for domain adaptation.