检索结果-内蒙古大学图书馆

Enhancing stock market prediction with extended coupled Hidden Markov Model over multi-sourced data

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Xi Li, Yixuan Wang, Senzhang Fang, Binxing Yu, Philip S. Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Ministry of Education Beijing China Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong Institute of Electronic and Information Engineering UESTC Guangdong China Department of Computer Science University of Illinois ChicagoIL United States Institute for Data Science Tsinghua University Beijing China

Traditional stock market prediction methods commonly only utilize the historical trading data, ignoring the fact that stock market uctuations can be impacted by various other information sources such as stock related events. Although some recent works propose event-driven prediction approaches by considering the event data, how to leverage the joint impacts of multiple data sources still remains an open research problem. In this work, we study how to explore multiple data sources to improve the performance of the stock prediction. We introduce an Extended Coupled Hidden Markov Model incorporating the news events with the historical trading data. To address the data sparsity issue of news events for each single stock, we further study the uctuation correlations between the stocks and incorporate the correlations into the model to facilitate the prediction task. Evaluations on China A-share market data in 2016 show the superior performance of our model against previous methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Hidden Markov models

Opportunities for nuclear physics & quantum information science

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Cloët, Ian C. Dietrich, Matthew R. Cloët, Ian C. Dietrich, Matthew R. Arrington, John Bazavov, Alexei Bishof, Michael Freese, Adam Gorshkov, Alexey V. Grassellino, Anna Hafidi, Kawtar Jacob, Zubin McGuigan, Michael Meurice, Yannick Meziani, Zein-Eddine Mueller, Peter Muschik, Christine Osborn, James Otten, Matthew Petreczky, Peter Polakovic, Tomas Poon, Alan Pooser, Raphael Roggero, Alessandro Saffman, Mark VanDevender, Brent Zhang, Jiehang Zohar, Erez Physics Division Argonne National Laboratory ArgonneIL60439 United States Department of Computational Mathematics Science and Engineering Michigan State University East LansingMI48824 United States Department of Physics and Astronomy Michigan State University East LansingMI48824 United States Joint Quantum Institute NIST/University of Maryland College ParkMD20742 United States Joint Center for Quantum Information and Computer Science NIST/University of Maryland College ParkMD20742 United States Fermi National Accelerator Laboratory Batavia IL60510 United States Northwestern University EvanstonIL60208 United States Birck Nanotechnology Center and Purdue Quantum Center School of Electrical and Computer Engineering Purdue University West LafayetteIN47906 United States Computational Science Initiative Brookhaven National Laboratory UptonNY11973 United States Department of Physics and Astronomy University of Iowa Iowa CityIA52242 United States Institute for Quantum Computing and Department of Physics and Astronomy University of Waterloo West Waterloo ON Canada ALCF Argonne National Laboratory ArgonneIL60439 United States Nanoscience and Technology Division Argonne National Laboratory ArgonneIL60439 United States Physics Department Brookhaven National Laboratory UptonNY11973 United States Physics and Material Science Divisions Argonne National Laboratory ArgonneIL60439 United States Institute for Nuclear and Particle Astrophysics and Nuclear Science Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Quantum Information Science Group Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak RidgeTN37831 United States Institute for Nuclear Theory University of Washington SeattleWA98195 United States Department of Physics University of Wisconsin MadisonWI53706 United States Pacific Northwest National Laboratory RichlandWA99354 United States Max Planck Institute of Quantum Opti

This whitepaper is an outcome of the workshop Intersections between Nuclear Physics and Quantum information held at Argonne National laboratory on 28-30 March 2018 [***/npqi2018/]. The workshop brought together 116 national and international experts in nuclear physics and quantum information science to explore opportunities for the two fields to collaborate on topics of interest to the U.S. department of Energy (DOE) Office of science, Office of Nuclear Physics, and more broadly to U.S. society and industry. The workshop consisted of 22 invited and 10 contributed talks, as well as three panel discussion sessions. Topics discussed included quantum computation, quantum simulation, quantum sensing, nuclear physics detectors, nuclear many-body problem, entanglement at collider energies, and lattice gauge theories. Copyright © 2019, The Authors. All rights reserved.

关键词： Lattice theory

Learning more robust features with adversarial training

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Shuangtao Chen, Yuanke Peng, Yanlin Bai, Lin Department of Computer Science and Technology Chengdu University of Technology Chengdu Sichuan China Department of Geological Engineering Chengdu University of Technology Chengdu Sichuan China Department of Information and Computing Sciences Chengdu University of Technology Chengdu Sichuan China Geomathematics Key Laboratory of Sichuan Province Chengdu Sichuan China

In recent years, it has been found that neural networks can be easily fooled by adversarial examples, which is a potential safety hazard in some safety-critical applications. Many researchers have proposed various method to make neural networks more robust to white-box adversarial attacks, but an effective method have not been found so far. In this short paper, we focus on the robustness of the features learned by neural networks. We show that the features learned by neural networks are not robust, and find that the robustness of the learned features is closely related to the resistance against adversarial examples of neural networks. We also find that adversarial training against fast gradients sign method (FGSM) does not make the leaned features very robust, even if it can make the trained networks very resistant to FGSM attack. Then we propose a method, which can be seen as an extension of adversarial training, to train neural networks to learn more robust features. We perform experiments on MNIST and CIFAR-10 to evaluate our method, and the experiment results show that this method greatly improves the robustness of neural networks and the features they learn. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

Modified cuckoo search ased neural networks for forest types classification 2

学校读者我要写书评

暂无评论

Modified cuckoo search ased neural networks for forest types...

2nd International Conference on information Technology and Intelligent Transportation Systems, ITITS 2017

作者： Chatterjee, Sankhadeep Dey, Nilanjan Sen, Soumya Ashour, Amira S. Fong, Simon James Shi, Fuqian Department of Computer Science and Engineering University of Calcutta Kolkata India Department of Information Technology Techno India College of Technology Kolkata India A. K. Choudhury School of Information Technology University of Calcutta Kolkata West Bengal India Department of Electronics and Electrical Communications Engineering Faculty of Engineering Tanta University Egypt Department of Computer and Information Science Data Analytics and Collaborative Computing Laboratory University of Macau Taipa China College of Information and Engineering Wenzhou Medical University Wenzhou China

ISBN: (纸本)9781614997849

Pixel classification in land scape images is a challenging process especially in forest images due to the similar spectral features of pixels situated close to each other. Previously, meta-heuristic coupled artificial neural network (ANN) models have been used to classify the two-different species, namely Japanese Cedar, Japanese Cypress and one mixed forest class. Previous attempts have shown reasonable improvement in the classification process using genetic algorithm (GA) supported neural network over other traditional approaches. Consequently, in the current work, a modified Cuckoo Search (CS) supported Neural Network (NN-MCS) classifier is proposed. The lévy flight associated with cuckoo search has been modified using McCulloch's method of generating stable random numbers. The proposed approach is compared with GA-NN using single objective function and CS-NN (ANN trained with CS) classifiers in terms of confusion matrix based performance metrics. The results depicted the dominance of the suggested NN-MCS model compared to the CS-NN model to a greater extent. © 2017 The authors and IOS Press. All rights reserved.

关键词： Neural networks

TensorFlow quantum: A software framework for quantum machine learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Broughton, Michael Verdon, Guillaume McCourt, Trevor Martinez, Antonio J. Yoo, Jae Hyeon Isakov, Sergei V. Massey, Philip Halavati, Ramin Niu, Murphy Yuezhen Zlokapa, Alexander Peters, Evan Lockwood, Owen Skolik, Andrea Jerbi, Sofiene Dunjko, Vedran Leib, Martin Streif, Michael Von Dollen, David Chen, Hongxiang Cao, Shuxiang Wiersema, Roeland Huang, Hsin-Yuan McClean, Jarrod R. Babbush, Ryan Boixo, Sergio Bacon, Dave Ho, Alan K. Neven, Hartmut Mohseni, Masoud Google Quantum Ai Mountain ViewCA United States Sandbox Alphabet Mountain ViewCA United States Google Mountain ViewCA United States Institute for Quantum Computing University of Waterloo WaterlooONN2L 3G1 Canada School of Computer Science University of Waterloo WaterlooONN2L 3G1 Canada Department of Applied Mathematics University of Waterloo WaterlooONN2L 3G1 Canada Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Physics and Astronomy University of Waterloo WaterlooONN2L 3G1 Canada Division of Physics Mathematics and Astronomy Caltech PasadenaCA91125 United States Fermi National Accelerator Laboratory P.O. Box 500 BataviaIL605010 United States Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States Data:Lab Volkswagen Group Ungererstr. 69 München80805 Germany Leiden University Niels Bohrweg 1 Leiden2333 CA Netherlands Institute for Theoretical Physics University of Innsbruck Technikerstr. 21a InnsbruckA-6020 Austria Institute of Theoretical Physics Staudtstr. 7 Erlangen91058 Germany Volkswagen Group Advanced Technologies San FranciscoCA94108 United States Rahko Ltd. Finsbury Park LondonN4 3JP United Kingdom Department of Computer Science University College London WC1E 6BT United Kingdom Clarendon Laboratory Department of Physics University of Oxford OxfordOX1 3PU United Kingdom Vector Institute MaRS Centre TorontoONM5G 1M1 Canada Department of Physics and Astronomy University of Waterloo ONN2L 3G1 Canada Institute for Quantum Information and Matter Caltech PasadenaCA United States Department of Computing and Mathematical Sciences Caltech PasadenaCA United States

We introduce TensorFlow Quantum (TFQ), an open source library for the rapid prototyping of hybrid quantum-classical models for classical or quantum data. This framework offers high-level abstractions for the design and training of both discriminative and generative quantum models under TensorFlow and supports high-performance quantum circuit simulators. We provide an overview of the software architecture and building blocks through several examples and review the theory of hybrid quantum-classical neural networks. We illustrate TFQ functionalities via several basic applications including supervised learning for quantum classification, quantum control, simulating noisy quantum circuits, and quantum approximate optimization. Moreover, we demonstrate how one can apply TFQ to tackle advanced quantum learning tasks including meta-learning, layerwise learning, Hamiltonian learning, sampling thermal states, variational quantum eigensolvers, classification of quantum phase transitions, generative adversarial networks, and reinforcement learning. We hope this framework provides the necessary tools for the quantum computing and machine learning research communities to explore models of both natural and artificial quantum systems, and ultimately discover new quantum algorithms which could potentially yield a quantum advantage. Copyright © 2020, The Authors. All rights reserved.

关键词： Open source software

Learning data-adaptive nonparametric kernels

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

An Open Source Map Optimization Platform for Efficient Navigation

学校读者我要写书评

暂无评论

An Open Source Map Optimization Platform for Efficient Navig...

IEEE International Conference on Computational science and engineering, CSE

作者： Liangming Cai Chunqiang Chen Xiaoling Wang Shurui Lin Kai Cheng Jiefeng Huang Jinping Jiang Minchen Zhu Min Du Rituparna Datta Yurong Li Jingshan Huang Zhicheng College College of Physics and Information Engineering Fuzhou University Fuzhou China University of South Alabama HaiXi Institutes Chinese Academy of Science Fuzhou China Zhicheng College Zhicheng College Fuzhou University Fuzhou China College of Allied Health Professions University of South Alabama Mobile USA Department of Respiratory Medicine Fujian Medical University Fuzhou China College of Electrical Engineering & Automation Fuzhou University Fuzhou China College of Mathematics and Computer Science Fuzhou University Fuzhou China Provincial Key Laboratory of Eco-industrial Green Technology Wuyi College Wuyishan China Fuzhou University School of Computing University of South Alabama Mobile USA Fuzhou University Fuzhou China

Aiming at the problem that the map operation time occupies more resources in the embedded system. By studying the digital map, then the corresponding map is drawn and the map is optimized. Using the GPS/BEIDOU module to locate and use the Dijkstra algorithm to achieve the shortest path of the navigation module design, the use of the map database to remove the corresponding area of the data mapping map information, in a translation to a certain distance when the scene clear the data, draw a map. In this way, there will be no data left in the view. Since the Dijkstra algorithm is based on the graph, it is necessary to link the roads in the area to create an indirect graph to find the shortest path to the end point. If the point of the line as an indirect node, the composition of the indirect map will be very large. Moreover, the use of the line as an indirect node, we can reduce the number of nodes without the map, to improve the efficiency of Dijkstra algorithm traversal. Based on the open system platform and data standard, this paper designs and develops a secure, stable and low cost embedded GPS/BEIDOU navigation and navigation system. The experimental results are optimized. The results show that the proposed method is efficient for navigation.

关键词： Conferences Scientific computing Ubiquitous computing

A novel unsupervised method for new word extraction

学校读者我要写书评

暂无评论

science China(information sciences) 2016年第9期59卷 11-21页

作者： Lili MEI Heyan HUANG Xiaochi WEI Xianling MAO Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Department of Computer Science and TechnologyBeijing Institute of Technology

New words could benefit many NLP tasks such as sentence chunking and sentiment analysis. However, automatic new word extraction is a challenging task because new words usually have no fixed language pattern, and even appear with the new meanings of existing words. To tackle these problems, this paper proposes a novel method to extract new words. It not only considers domain specificity, but also combines with multiple statistical language knowledge. First, we perform a filtering algorithm to obtain a candidate list of new words. Then, we employ the statistical language knowledge to extract the top ranked new words. Experimental results show that our proposed method is able to extract a large number of new words both in Chinese and English corpus, and notably outperforms the state-of-the-art methods. Moreover, we also demonstrate our method increases the accuracy of Chinese word segmentation by 10% on corpus containing new words.

关键词： new word extraction word segmentation domain specificity statistical language knowledge domain word extraction

Erratum to: Search for squarks and gluinos in final states with one isolated lepton, jets, and missing transverse momentum at s = 13 TeV with the ATLAS detector

学校读者我要写书评

暂无评论

The European Physical Journal C 2021年第10期81卷 1-15页

作者： Aad, G. Abbott, B. Abbott, D. C. Abed Abud, A. Abeling, K. Abhayasinghe, D. K. Abidi, S. H. AbouZeid, O. S. Abraham, N. L. Abramowicz, H. Abreu, H. Abulaiti, Y. Acharya, B. S. Achkar, B. Adam, L. Adam Bourdarios, C. Adamczyk, L. Adamek, L. Adelman, J. Adiguzel, A. Adorni, S. Adye, T. Affolder, A. A. Afik, Y. Agapopoulou, C. Agaras, M. N. Aggarwal, A. Agheorghiesei, C. Aguilar-Saavedra, J. A. Ahmad, A. Ahmadov, F. Ahmed, W. S. Ai, X. Aielli, G. Akatsuka, S. Akbiyik, M. Åkesson, T. P. A. Akilli, E. Akimov, A. V. Al Khoury, K. Alberghi, G. L. Albert, J. Alconada Verzini, M. J. Alderweireldt, S. Aleksa, M. Aleksandrov, I. N. Alexa, C. Alexopoulos, T. Alfonsi, A. Alfonsi, F. Alhroob, M. Ali, B. Ali, S. Aliev, M. Alimonti, G. Allaire, C. Allbrooke, B.M. M. Allen, B. W. Allport, P. P. Aloisio, A. Alonso, F. Alpigiani, C. Alunno Camelia, E. Alvarez Estevez, M. Alviggi, M. G. Amaral Coutinho, Y. Ambler, A. Ambroz, L. Amelung, C. Amidei, D. Amor Dos Santos, S. P. Amoroso, S. Amrouche, C. S. An, F. Anastopoulos, C. Andari, N. Andeen, T. Anders, J. K. Andrean, S. Y. Andreazza, A. Andrei, V. Anelli, C. R. Angelidakis, S. Angerami, A. Anisenkov, A. V. Annovi, A. Antel, C. Anthony, M. T. Antipov, E. Antonelli, M. Antrim, D.J. A. Anulli, F. Aoki, M. Aparisi Pozo, J. A. Aparo, M. A. Aperio Bella, L. Aranzabal, N. Araujo Ferraz, V. Araujo Pereira, R. Arcangeletti, C. Arce, A.T. H. Arguin, J.-F. Argyropoulos, S. Arling, J.-H. Armbruster, A. J. Armstrong, A. Arnaez, O. Arnold, H. Arrubarrena Tame, Z. P. Artoni, G. Asada, H. Asai, K. Asai, S. Asawatavonvanich, T. Asbah, N. Asimakopoulou, E. M. Asquith, L. Assahsah, J. Assamagan, K. Astalos, R. Atkin, R. J. Atkinson, M. Atlay, N. B. Atmani, H. Atmasiddha, P. A. Augsten, K. Austrup, V. A. Avolio, G. Ayoub, M. K. Azuelos, G. Babal, D. Bachacou, H. Bachas, K. Backman, F. Bagnaia, P. Bahmani, M. Bahrasemani, H. Bailey, A. J. Bailey, V. R. Baines, J. T. Bakalis, C. Baker, O. K. Bakker, P. J. Bakos, E. Bakshi Gupta, D. Balaji, S. Balasubramanian, R. Baldin, E. M. Balek, P. Balli, F. Balunas CPPM Aix-Marseille Université CNRS/IN2P3 Marseille France Homer L. Dodge Department of Physics and Astronomy University of Oklahoma Norman USA Department of Physics University of Massachusetts Amherst USA CERN Geneva Switzerland II. Physikalisches Institut Georg-August-Universität Göttingen Göttingen Germany Department of Physics Royal Holloway University of London Egham UK Department of Physics University of Toronto Toronto Canada Niels Bohr Institute University of Copenhagen Copenhagen Denmark Department of Physics and Astronomy University of Sussex Brighton UK Raymond and Beverly Sackler School of Physics and Astronomy Tel Aviv University Tel Aviv Israel Department of Physics Technion Israel Institute of Technology Haifa Israel High Energy Physics Division Argonne National Laboratory Argonne USA INFN Gruppo Collegato di Udine Sezione di Trieste Udine Italy ICTP Trieste Italy Department of Physics King’s College London London UK Institut für Physik Universität Mainz Mainz Germany LAPP Université Grenoble Alpes Université Savoie Mont Blanc CNRS/IN2P3 Annecy France AGH University of Science and Technology Faculty of Physics and Applied Computer Science Kraków Poland Department of Physics Northern Illinois University DeKalb USA Department of Physics Bogazici University Istanbul Turkey Dept. of Physics Istanbul University Istanbul Turkey Département de Physique Nucléaire et Corpusculaire Université de Genève Geneva Switzerland Particle Physics Department Rutherford Appleton Laboratory Didcot UK Santa Cruz Institute for Particle Physics University of California Santa Cruz Santa Cruz USA IJCLab CNRS/IN2P3 Université Paris-Saclay Orsay France LPC Université Clermont Auvergne CNRS/IN2P3 Clermont-Ferrand France Institute for Mathematics Astrophysics and Particle Physics Radboud University/Nikhef Nijmegen The Netherlands Department of Physics Alexandru Ioan Cuza University of Iasi Iasi Romania Laboratório de Instrumentação e Física E

A correction to this paper has been published: 10.1140/epjc/s10052-021-09344-w

关键词：