2018/06/15(Fri) 14:20 - Prof. Jen-Tzung Chien (National Chiao Tung University) - Deep Neural Network Learning
Topic:
Deep Neural Network Learning
Speaker:
Prof. Jen-Tzung Chien (Department of Electrical and Computer Engineering, National Chiao Tung University)
Date:
2018/06/15
Time:
14:20 ~16:20
Location:
Delta Building R216, NTHU
Abstract:
In this talk, I will present a variety of learning strategies to deal with different issues in deep neural network. In tensor factorized neural network, a tensor factorized error backpropagation algorithm is developed to preserve the structure of tensor inputs in layer-wise network during training a classification network. We further present a semi-supervised learning for domain adaptation based on neural network model which jointly minimizes the divergence between the distributions in source and target domains, the reconstruction errors due to an auto-encoder, and the classification errors due to the labeled data. Finally, a deep unfolding inference is proposed to integrate the benefits from model-based method and neural network model. A deep unfolded topic model is proposed. A number of applications and future works will be addressed.
Bio:
Jen-Tzung Chien received his Ph.D. degree in electrical engineering from National Tsing Hua University in 1997. He is now with the Department of Electrical and Computer Engineering, National Chiao Tung University. His research interests include machine learning, deep learning, natural language processing and computer vision.
Deep Neural Network Learning
Speaker:
Prof. Jen-Tzung Chien (Department of Electrical and Computer Engineering, National Chiao Tung University)
Date:
2018/06/15
Time:
14:20 ~16:20
Location:
Delta Building R216, NTHU
Abstract:
In this talk, I will present a variety of learning strategies to deal with different issues in deep neural network. In tensor factorized neural network, a tensor factorized error backpropagation algorithm is developed to preserve the structure of tensor inputs in layer-wise network during training a classification network. We further present a semi-supervised learning for domain adaptation based on neural network model which jointly minimizes the divergence between the distributions in source and target domains, the reconstruction errors due to an auto-encoder, and the classification errors due to the labeled data. Finally, a deep unfolding inference is proposed to integrate the benefits from model-based method and neural network model. A deep unfolded topic model is proposed. A number of applications and future works will be addressed.
Bio:
Jen-Tzung Chien received his Ph.D. degree in electrical engineering from National Tsing Hua University in 1997. He is now with the Department of Electrical and Computer Engineering, National Chiao Tung University. His research interests include machine learning, deep learning, natural language processing and computer vision.