145 citations · 265 across the 18 of their papers we have counts for
8 papers · 1 filter
Regularizing Neural Networks via Adversarial Model Perturbation
Yaowei Zheng, Richong Zhang, Yongyi Mao
Effective regularization techniques are highly desired in deep learning for alleviating overfitting and improving generalization. This work proposes a new regularization scheme, ba…
Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers
Masoumeh Soflaei, Hongyu Guo, Ali Al-Bashabsheh +2
We consider the problem of learning a neural network classifier. Under the information bottleneck (IB) principle, we associate with this classification problem a representation lea…
MixUp as Directional Adversarial Training
Guillaume P. Archambault, Yongyi Mao, Hongyu Guo +1
In this work, we explain the working mechanism of MixUp in terms of adversarial training. We introduce a new class of adversarial training schemes, which we refer to as directional…
Understanding Feature Selection and Feature Memorization in Recurrent Neural Networks
Bokang Zhu, Richong Zhang, Dingkun Long +1
In this paper, we propose a test, called Flagged-1-Bit (F1B) test, to study the intrinsic capability of recurrent neural networks in sequence learning. Four different recurrent net…
MixUp as Locally Linear Out-Of-Manifold Regularization
Hongyu Guo, Yongyi Mao, Richong Zhang
MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their label…
Aggregated Learning: A Deep Learning Framework Based on Information-Bottleneck Vector Quantization
Hongyu Guo, Yongyi Mao, Ali Al-Bashabsheh +1
Based on the notion of information bottleneck (IB), we formulate a quantization problem called "IB quantization". We show that IB quantization is equivalent to learning based on th…
Prototypical Recurrent Unit
Dingkun Long, Richong Zhang, Yongyi Mao
Despite the great successes of deep learning, the effectiveness of deep neural networks has not been understood at any theoretical depth. This work is motivated by the thrust of de…
On the representation and embedding of knowledge bases beyond binary relations
Jianfeng Wen, Jianxin Li, Yongyi Mao +2
The models developed to date for knowledge base embedding are all based on the assumption that the relations contained in knowledge bases are binary. For the training and testing o…