Incorporating Hidden Layer representation into Adversarial Attacks and Defences

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 […]


Continue.. Incorporating Hidden Layer representation into Adversarial Attacks and Defences

On the Convergence of Reinforcement Learning in Nonlinear Continuous State Space Problems

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 […]


Continue.. On the Convergence of Reinforcement Learning in Nonlinear Continuous State Space Problems

Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification

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 […]


Continue.. Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification

A Review of Generalized Zero-Shot Learning Methods

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 […]


Continue.. A Review of Generalized Zero-Shot Learning Methods

SED Analysis of 13 Spectroscopically Confirmed Galaxies at z$simeq$6 to Constrain UV-Slope, Model Dust Attenuation and Escape Fractions

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 […]


Continue.. SED Analysis of 13 Spectroscopically Confirmed Galaxies at z$simeq$6 to Constrain UV-Slope, Model Dust Attenuation and Escape Fractions

Exciting modes due to the aberration of gravitational waves: Measurability for extreme-mass-ratio inspirals

Kavli Affiliate: Pau Amaro Seoane | First 5 Authors: Alejandro Torres-Orjuela, Pau Amaro Seoane, Zeyuan Xuan, Alvin J. K. Chua, María J. B. Rosell | Summary: Gravitational waves from a source moving relative to us can suffer from special-relativistic effects such as aberration. The required velocities for these to be significant are on the order […]


Continue.. Exciting modes due to the aberration of gravitational waves: Measurability for extreme-mass-ratio inspirals

Assessing Classifier Fairness with Collider Bias

Kavli Affiliate: Ke Wang | First 5 Authors: Zhenlong Xu, Ziqi Xu, Jixue Liu, Debo Cheng, Jiuyong Li | Summary: The increasing application of machine learning techniques in everyday decision-making processes has brought concerns about the fairness of algorithmic decision-making. This paper concerns the problem of collider bias which produces spurious associations in fairness assessment […]


Continue.. Assessing Classifier Fairness with Collider Bias

A Tale of Two Transition Disks: ALMA long-baseline observations of ISO-Oph 2 reveal two closely packed non-axisymmetric rings and a $sim$2 au cavity

Kavli Affiliate: Gregory J. Herczeg | First 5 Authors: Camilo González-Ruilova, Lucas A. Cieza, Antonio S. Hales, Sebastián Pérez, Alice Zurlo | Summary: ISO-Oph 2 is a wide-separation (240 au) binary system where the primary star harbors a massive (M$_{dust}$ $sim$40 M$_{oplus}$) ring-like disk with a dust cavity $sim$50 au in radius and the secondary […]


Continue.. A Tale of Two Transition Disks: ALMA long-baseline observations of ISO-Oph 2 reveal two closely packed non-axisymmetric rings and a $sim$2 au cavity

Teacher-Critical Training Strategies for Image Captioning

Kavli Affiliate: Jiansheng Chen | First 5 Authors: Yiqing Huang, Jiansheng Chen, , , | Summary: Existing image captioning models are usually trained by cross-entropy (XE) loss and reinforcement learning (RL), which set ground-truth words as hard targets and force the captioning model to learn from them. However, the widely adopted training strategies suffer from […]


Continue.. Teacher-Critical Training Strategies for Image Captioning

The First Extensive Spectroscopic Study of Young Stars in the North America and Pelican Nebulae Region

Kavli Affiliate: Gregory J. Herczeg | First 5 Authors: Min Fang, Lynne A. Hillenbrand, Jinyoung Serena Kim, Krzysztof Findeisen, Gregory J. Herczeg | Summary: We present a spectroscopic survey of over 3400 potential members in the North America and Pelican nebulae (NAP) using several low-resolution ($Rapprox$ 1300-2000) spectrographs: Palomar/Norris, WIYN/HYDRA, Keck/DEIMOS, and MMT/Hectospec. We identify […]


Continue.. The First Extensive Spectroscopic Study of Young Stars in the North America and Pelican Nebulae Region