78 citations · 186 across the 16 of their papers we have counts for
9 papers · 1 filter
Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module
Wei-Cheng Tseng, Wei Wei, Da-Cheng Juan +1
Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can…
COCO-GAN: Generation by Parts via Conditional Coordinating
Chieh Hubert Lin, Chia-Che Chang, Yu-Sheng Chen +3
Humans can only interact with part of the surrounding environment due to biological restrictions. Therefore, we learn to reason the spatial relationships across a series of observa…
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…
InstaNAS: Instance-aware Neural Architecture Search
An-Chieh Cheng, Chieh Hubert Lin, Da-Cheng Juan +2
Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives suc…
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,…
Escaping from Collapsing Modes in a Constrained Space
Chia-Che Chang, Chieh Hubert Lin, Che-Rung Lee +3
Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training. We study the issue of mode collapse of Boundary Equilibrium Generative Adver…
HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks
Dimitrios Stamoulis, Ermao Cai, Da-Cheng Juan +1
While selecting the hyper-parameters of Neural Networks (NNs) has been so far treated as an art, the emergence of more complex, deeper architectures poses increasingly more challen…
NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis +1
"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from…