Kavli Affiliate: Ran Wang | First 5 Authors: Haojing Shen, Sihong Chen, Ran Wang, Xizhao Wang, | Summary: In this paper, we propose a defence strategy to improve adversarial robustness by incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input information including adversarial perturbation. And this defence strategy […]
Kavli Affiliate: Ran Wang | First 5 Authors: Raman Goyal, Suman Chakravorty, Ran Wang, Mohamed Naveed Gul Mohamed, | Summary: We consider the problem of Reinforcement Learning for nonlinear stochastic dynamical systems. We show that in the RL setting, there is an inherent “Curse of Variance" in addition to Bellman’s infamous “Curse of Dimensionality", in […]
Kavli Affiliate: Rainer Spurzem | First 5 Authors: Shiyan Zhong, Kimitake Hayasaki, Shuo Li, Peter Berczik, Rainer Spurzem | Summary: Tidal disruption events (TDEs) probe properties of supermassive black holes (SMBHs), their accretion disks, and the surrounding nuclear stellar cluster. Light curves of TDEs are related to orbital properties of stars falling SMBHs. We study […]
Kavli Affiliate: Rainer Spurzem | First 5 Authors: Shiyan Zhong, Kimitake Hayasaki, Shuo Li, Peter Berczik, Rainer Spurzem | Summary: Tidal disruption events (TDEs) provide a clue to the properties of a central supermassive black hole (SMBH) and an accretion disk around it, and to the stellar density and velocity distributions in the nuclear star […]
Kavli Affiliate: Jiansheng Chen | First 5 Authors: Weitao Wan, Jiansheng Chen, Cheng Yu, Tong Wu, Yuanyi Zhong | Summary: The softmax cross-entropy loss function has been widely used to train deep models for various tasks. In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification. Unlike […]
Kavli Affiliate: Ran Wang | First 5 Authors: Farhad Pourpanah, Moloud Abdar, Yuxuan Luo, Xinlei Zhou, Ran Wang | Summary: Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To address this challenging task, GZSL leverages semantic information of […]
Kavli Affiliate: Renxin Xu | First 5 Authors: Renxin Xu, Xiaoyu Lai, Chengjun Xia, , | Summary: What if normal baryonic matter is compressed so tightly that atomic nuclei come into close contact? This question has been asked since 1930s. The fist answer was presented by Lev Landau whose speculation has been developed, and the […]
Kavli Affiliate: Linhua Jiang | First 5 Authors: Junehyoung Jeon, Rogier Windhorst, Seth H. Cohen, Rolf A. Jansen, Brent M. Smith | Summary: The reionization of the hydrogen in the Universe is thought to have completed by redshift $zsimeq5.5-6$. To probe this era, galaxy observations in the Subaru Deep Field (SDF) have identified more than […]
Kavli Affiliate: Renxin Xu | First 5 Authors: Hua Feng, Hong Li, Xiangyun Long, Ronaldo Bellazzini, Enrico Costa | Summary: The Crab nebula is so far the only celestial object with a statistically significant detection in soft x-ray polarimetry, a window that has not been explored in astronomy since the 1970s. However, soft x-ray polarimetry […]
Kavli Affiliate: Renxin Xu | First 5 Authors: Shi Dai, Jiguang Lu, Chen Wang, Weiyang Wang, Renxin Xu | Summary: Fast spinning (e.g., sub-second) neutron star with ultra-strong magnetic fields (or so-called magnetar) is one of the promising origins of repeating fast radio bursts (FRBs). Here we discuss circularly polarised emissions produced by propagation effects […]