147 citations · 189 across the 9 of their papers we have counts for
9 papers
Contextual Temperature for Language Modeling
Pei-Hsin Wang, Sheng-Iou Hsieh, Shih-Chieh Chang +4
Temperature scaling has been widely used as an effective approach to control the smoothness of a distribution, which helps the model performance in various tasks. Current practices…
Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization
Li-Huang Tsai, Shih-Chieh Chang, Yu-Ting Chen +3
Analog computing hardwares, such as Processing-in-memory (PIM) accelerators, have gradually received more attention for accelerating the neural network computations. However, PIM a…
Learning with Hierarchical Complement Objective
Hao-Yun Chen, Li-Huang Tsai, Shih-Chieh Chang +4
Label hierarchies widely exist in many vision-related problems, ranging from explicit label hierarchies existed in image classification to latent label hierarchies existed in seman…
Complement Objective Training
Hao-Yun Chen, Pei-Hsin Wang, Chun-Hao Liu +5
Learning with a primary objective, such as softmax cross entropy for classification and sequence generation, has been the norm for training deep neural networks for years. Although…
Improving Adversarial Robustness via Guided Complement Entropy
Hao-Yun Chen, Jhao-Hong Liang, Shih-Chieh Chang +4
Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent meth…
Searching Toward Pareto-Optimal Device-Aware Neural Architectures
An-Chieh Cheng, Jin-Dong Dong, Chi-Hung Hsu +7
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However,…
MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
Chi-Hung Hsu, Shu-Huan Chang, Jhao-Hong Liang +7
Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures. While most existing works aim a…
Task Transfer by Preference-Based Cost Learning
Mingxuan Jing, Xiaojian Ma, Wenbing Huang +2
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action plan…
DC-Prophet: Predicting Catastrophic Machine Failures in DataCenters
You-Luen Lee, Da-Cheng Juan, Xuan-An Tseng +2
When will a server fail catastrophically in an industrial datacenter? Is it possible to forecast these failures so preventive actions can be taken to increase the reliability of a…