检索结果-内蒙古大学图书馆

Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Hongcheng Wang, Yuxuan Zhong, Fangwei Wu, Mingdong Zhang, Jianwei Wang, Yizhou Dong, Hao School of Computer Science Peking University Beijing100871 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China School of Intelligence and Technology Peking University National Key Laboratory of General Artificial Intelligence BIGAI Beijing100871 China TAMS Department of Informatics Universität Hamburg Germany The Center on Frontiers of Computing Studies Institute for Artificial Intelligence Peking University Beijing100871 China The Nat’l Eng. Research Center of Visual Technology Beijing100871 China

Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, e.g., household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories;2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Relating entropies of quantum channels

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kurzyk, Dariusz Pawela, Lukasz Puchala, Zbigniew Institute of Theoretical and Applied Informatics Polish Academy of Sciences ul. Baltycka 5 Gliwice44-100 Poland Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University ul. Lojasiewicza 11 Kraków30-348 Poland

In this work, we study two different approaches to defining the entropy of a quantum channel. One of these is based on the von Neumann entropy of the corresponding Choi-Jamiolkowski state. The second one is based on the relative entropy of the output of the extended channel relative to the output of the extended completely depolarizing channel. This entropy then needs to be optimized over all possible input states. Our results first show that the former entropy provides an upper bound on the latter. Next, we show that for unital qubit channels, this bound is saturated. Finally, we conjecture and provide numerical intuitions that the bound can also be saturated for random channels as their dimension tends to infinity. © 2021, CC BY.

关键词： Entropy

EXCLUDING FALSE NEGATIVE ERROR IN CERTIFICATION OF QUANTUM CHANNELS

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Krawiec, Aleksandra Pawela, Lukasz Puchala, Zbigniew Institute of Theoretical and Applied Informatics Polish Academy of Sciences ul. Baltycka 5 Gliwice44-100 Poland Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University ul. Lojasiewicza 11 Kraków30-348 Poland

Certification of quantum channels is based on quantum hypothesis testing and involves also preparation of an input state and choosing the final measurement. This work primarily focuses on the scenario when the false negative error cannot occur, even if it leads to the growth of the probability of false positive error. We establish a condition when it is possible to exclude false negative error after a finite number of queries to the quantum channel in parallel, and we provide an upper bound on the number of queries. On top of that, we found a class of channels which allow for excluding false negative error after a finite number of queries in parallel, but cannot be distinguished unambiguously. Moreover, it will be proved that parallel certification scheme is always sufficient, however the number of steps may be decreased by the use of adaptive scheme. Finally, we consider examples of certification of various classes of quantum channels and measurements. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum entanglement

MES Systems as an Integral Part of Digital Production 13

学校读者我要写书评

暂无评论

MES Systems as an Integral Part of Digital Production

13th International Conference Management of Large-Scale System Development, MLSD 2020

作者： Makarov, V.V. Frolov, Ye.B. Parshina, I.S. Ushakova, M.V. Institute of Control Sciences of Russian Academy of Sciences Laboratory of Identification of Control Systems Moscow Russia Moscow State University of Technology Stankin Department of Information Technologies and Computer Systems Moscow Russia National University of Science and Technology Misis Department of Business Informatics and Production Management Moscow Russia

ISBN: (纸本)9781728110943

This article considers issues of place and role of MES systems in digital production. The types of factories of the future and their main characteristics are demonstrated. The abilities of a digital platform for the car industry are revealed. The necessity of transforming business processes using integrated cyber-physical systems (CPS systems) is proved. © 2020 IEEE.

关键词： Automotive industry

HUNTER: AI based holistic resource management for sustainable cloud computing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tuli, Shreshth Gill, Sukhpal Singh Xu, Minxian Garraghan, Peter Bahsoon, Rami Prof, Scharam Dustdar Sakellariou, Rizos Rana, Omer Buyya, Rajkumar Casale, Giuliano Jennings, Nicholas R. Department of Computing Imperial College London United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China School of Computing and Communications Lancaster University United Kingdom School of Computer Science University of Birmingham United Kingdom Distributed Systems Group Vienna University of Technology Austria Department of Computer Science University of Manchester United Kingdom School of Computer Science and Informatics Cardiff University United Kingdom Laboratory School of Computing and Information Systems The University of Melbourne Australia

The worldwide adoption of cloud data centers (CDCs) has given rise to the ubiquitous demand for hosting application services on the cloud. Further, contemporary data-intensive industries have seen a sharp upsurge in the resource requirements of modern applications. This has led to the provisioning of an increased number of cloud servers, giving rise to higher energy consumption and, consequently, sustainability concerns. Traditional heuristics and reinforcement learning based algorithms for energy-efficient cloud resource management address the scalability and adaptability related challenges to a limited extent. Existing work often fails to capture dependencies across thermal characteristics of hosts, resource consumption of tasks and the corresponding scheduling decisions. This leads to poor scalability and an increase in the compute resource requirements, particularly in environments with non-stationary resource demands. To address these limitations, we propose an artificial intelligence (AI) based holistic resource management technique for sustainable cloud computing called HUNTER. The proposed model formulates the goal of optimizing energy efficiency in data centers as a multi-objective scheduling problem, considering three important models: energy, thermal and cooling. HUNTER utilizes a Gated Graph Convolution Network as a surrogate model for approximating the Quality of Service (QoS) for a system state and generating optimal scheduling decisions. Experiments on simulated and physical cloud environments using the CloudSim toolkit and the COSCO framework show that HUNTER outperforms state-of-the-art baselines in terms of energy consumption, SLA violation, scheduling time, cost and temperature by up to 12, 35, 43, 54 and 3 percent respectively. © 2021, CC BY.

关键词： Energy efficiency

Deep deformation detail synthesis for thin shell models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Lan Gao, Lin Yang, Jie Xu, Shibiao Ye, Juntao Zhang, Xiaopeng Lai, Yu-Kun Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device China Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences Beijing China Visual Computing Group School of Computer Science and Informatics Cardiff University Wales United Kingdom

In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make efforts to reduce the computation significantly by utilizing a preprocessed database. One type of methods relies on human poses to synthesize fitted garments, but these methods cannot be applied to general cloth animations. Another type of methods adds details to the coarse meshes, which does not have such restrictions. However, existing works usually utilize coordinate-based representations which cannot cope with large-scale deformation, and requires dense vertex correspondences between coarse and fine meshes. Moreover, as such methods only add details, they require coarse meshes to be sufficiently close to fine meshes, which can be either impossible, or require unrealistic constraints to be applied when generating fine meshes. To address these challenges, we develop a temporally and spatially as-consistent-as-possible deformation representation (named TS-ACAP) and design a DeformTransformer network to learn the mapping from low-resolution meshes to ones with fine details. This TS-ACAP representation is designed to ensure both spatial and temporal consistency for sequential large-scale deformations from cloth animations. With this TS-ACAP representation, our DeformTransformer network first utilizes two mesh-based encoders to extract the coarse and fine features using shared convolutional kernels, respectively. To transduct the coarse features to the fine ones, we leverage the Transformer network that consists of frame-level attention mechanisms to ensure temporal coherence of the prediction. Experimental results show that our method is able to produce reliable and realistic animations in various datasets at high frame rates: 10 ∼ 35 times faster than physics-based simulation, with superior detail synthesis abilities compared to existing methods. Copyright © 2021, The Authors. All rights r

关键词： Deformation

Evolution Stage Identification of Haze Pollution Episodes Over the North China Plain Using Constrained Dynamic Time Warping and Multiway Principal Component Analysis

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zhang, Hao Ran, Jinye Yu, Junyi Zhu, Morui Jia, Zihan Wang, Ying Li, Hengqi Jiao, Yongli School of Chemistry and Chemical Engineering Southwest University Chongqing400715 China College of Computer and Information Science Southwest University Chongqing400715 China Dalian National Laboratory for Clean Energy Dalian Institute of Chemical Physics Chinese Academy of Sciences Dalian116023 China Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest1111 Hungary Science in Business Administration Bryant University RI02917 United States Shanghai201204 China

To divide haze pollution episodes into different types, dynamic time warping (DTW) distance is employed to calculate the dissimilarities of different episodes. Then, a multiway principal component analysis (MPCA) method based on the constrained DTW, which is used to adjust episodes of different duration to the same length, is carried out to identify different evolution stage of each episode automatically according to the change rate of the first principal component in MPCA model. Contribution rates of meteorological factors and other air pollutant to the fluctuation of PM2.5 concentrations in different evolution stages are also calculated using the contributions to the principal component subspace. Results show that each episode consists of an early formational stage, an accumulation stage, a steady stage, and a clearing stage. © 2022, The Authors. All rights reserved.

关键词： Principal component analysis

Combining Attentional CNN and GRU Networks for Ocean Current Prediction based on HF Radar Observations 19

学校读者我要写书评

暂无评论

Combining Attentional CNN and GRU Networks for Ocean Current...

Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition

作者： Nathachai Thongniran Kulsawasd Jitkajornwanich Siam Lawawirojwong Panu Srestasathiern Peerapon Vateekul Department of Computer Engineering Chulalongkorn University Department of Computer Science King Mongkut's Institute of Technology Ladkrabang GISTDA Academy Geo-Informatics & Space Technology Development Agency

ISBN: (纸本)9781450376570

Lately, CNN-GRU demonstrates the ability of deep learning techniques on ocean surface current prediction. Improvement of the current prediction model creates positive impact on variety of marine activities, such as search-and-rescue, disaster monitoring and power forecasting. Deep learning techniques was successfully deployed to improve model performance in many areas due to their ability to handle enormous amounts of information in a variety of inputs and their huge growth in recent years. Latest ocean current prediction employed a combination of two mature techniques, which are Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU), to capture spatial and temporal characteristics of its nature. However, there is still room for improvement due to many modern techniques that still have not been employed, and domain knowledge in oceanic, such as lunar illumination, is not taken into account to improve prediction performance. This paper introduces the ocean surface prediction model that employs soft attention mechanism, transfer learning, and incorporation of domain knowledge inputs which are month number, lunar effect, and hour number. An experimental dataset from 2014 to 2016, provided by GISTDA, is collected by using high frequency (HF) radar stations located along the coastal Gulf of Thailand. The experiment compares an existing CNN-GRU and our proposed model. The result shows an improvement of the prediction model in terms of RMSE by 2.57%, and 3.44% on U and V components.

关键词： convolutional neural network deep learning HF radar gated recurrent unit spatio-temporal Surface current forecasting attention mechanism transfer learning

A survey on deep geometry learning: From a representation perspective

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xiao, Yun-Peng Lai, Yu-Kun Zhang, Fang-Lue Li, Chunpeng Gao, Lin Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Informatics Cardiff University Wales United Kingdom School of Engineering and Computer Science Victoria University of Wellington New Zealand

Researchers have now achieved great success on dealing with 2D images using deep learning. In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention. Many advanced techniques for 3D shapes have been proposed for different applications. Unlike 2D images, which can be uniformly represented by regular grids of pixels, 3D shapes have various representations, such as depth and multi-view images, voxel-based representation, point-based representation, mesh-based representation, implicit surface representation, etc. However, the performance for different applications largely depends on the representation used, and there is no unique representation that works well for all applications. Therefore, in this survey, we review recent development in deep learning for 3D geometry from a representation perspective, summarizing the advantages and disadvantages of different representations in different applications. We also present existing datasets in these representations and further discuss future research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Geometry