作者：
Chen, LiangDong, MingBagci, Hakan
Electrical and Computer Engineering Program Computer Electrical and Mathematical Science and Engineering Division Thuwal23955-6900 Saudi Arabia
Output saturation observed for high power levels of input optical pump is a well-known bottleneck in the operation of terahertz photoconductive devices (PCDs). This saturation is a result of various screening effects ...
详细信息
Estimating the homography between two images is crucial for mid- or high-level vision tasks, such as image stitching and fusion. However, using supervised learning methods is often challenging or costly due to the dif...
作者：
Dong, MingChen, LiangBagci, Hakan
Computer Electrical and Mathematical Science and Engineering Division Electrical and Computer Engineering Program Thuwal23955-6900 Saudi Arabia
A time domain discontinuous Galerkin (DGTD)-based framework is developed to analyze three-dimensional organic electrochemical transistors (OECTs). The proposed framework uses a local DG scheme to discretize the (non-l...
详细信息
Under voltage load shedding (UVLS) for power grid emergency control builds the last defensive perimeter to prevent cascade outages and blackouts in case of contingencies. This letter proposes a novel cooperative multi...
详细信息
Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined. However, imitation learning methods...
详细信息
Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined. However, imitation learning methods still require numerous expert demonstration samples to successfully imitate an expert's behavior. To improve sample efficiency, we utilize self-supervised representation learning, which can generate vast training signals from the given data. In this study, we propose a self-supervised representation-based adversarial imitation learning method to learn state and action representations that are robust to diverse distortions and temporally predictive, on non-image control tasks. In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions. We theoretically and empirically observe that making an informative feature manifold with less sample complexity significantly improves the performance of imitation learning. The proposed method shows a 39% relative improvement over existing adversarial imitation learning methods on MuJoCo in a setting limited to 100 expert state-action pairs. Moreover, we conduct comprehensive ablations and additional experiments using demonstrations with varying optimality to provide insights into a range of factors.
Current advances in deep learning have brought various breakthroughs in processing medical data. However, dealing with a limited number of medical datasets remains a challenge in deep learning and often leads to overf...
详细信息
Dealing with class imbalance is a significant issue in classification tasks that often leads to lower prediction performance. Many data augmentation methods have been suggested to tackle this problem, but their effect...
详细信息
暂无评论