检索结果-内蒙古大学图书馆

Learning Spatial and Temporal Information with Complex-Valued Operation for High-Performance of Spiking Neural Networks

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Liu, Fang Pedrycz, Witold Xu, Qi Xu, Jialin Yang, Jie Wu, Wei School of Mathematical Sciences Dalian University of Technology Dalian116024 China Key Laboratory for Computational Mathematics and Data Intelligence of Liaoning Province Dalian116024 China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland School of Artificial Intelligence Dalian University of Technology Dalian116024 China

Every neuron in traditional spiking neural networks (SNNs) only transmits temporal information, namely spiking time, to its postsynaptic neurons while all other underlying information is discarded. In view that brain pathways for temporal and spatial cognition involve overlapping and interacting systems that converge on the hippocampal region, in this study, we show for the first time that spatial and temporal information can move forward simultaneously, interact, and finally fuse in the output layer as the brain system works by implementing the complex-valued operations in SNNs. The spatial information is extracted with the derivative of membrane potential function of spiking neuron at the moment of excitation and the temporal information is the spiking time. Accuracy and generalization ability of neural network outputs from seven benchmark classification datasets are found to be excellent. The networks are also able to process regression tasks, which is unachievable by most of the existing SNNs. © 2022, The Authors. All rights reserved.

关键词： Neurons

Pseudo Oversampling Based on Feature Transformation and Fuzzy Membership Functions for Imbalanced and Overlapping Data

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Pan, Tingting Pedrycz, Witold Yang, Jie School of Mathematical Sciences Tiangong University Tianjin Tianjin300387 China Department of Electrical and Computer Engineering University of Alberta AB-Alberta EdmontonT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Mazowiekie Warsaw00-901 Poland Faculty of Engineering and Natural Sciences Department of Computer Engineering Istinye University Sariyer Istanbul34460 Turkey School of Mathematical Sciences Dalian University of Technology Liaoning Dalian116024 China Key Laboratory for Computational Mathematics and Data Intelligence of Liaoning Province Liaoning Dalian116024 China

The class imbalance in data can lead to significant challenges for classifier learning and has attracted increased attention in the fields of data mining and machine learning. Additionally, the occurrence of class overlap, which is also commonly observed in real-world data, further exacerbates the learning difficulty. In this paper, we propose a novel pseudo oversampling method (POM) for imbalanced and overlapping data. It is motivated by the point that overlapping samples from different classes share the same distribution space, and therefore information underlying in majority (negative) overlapping samples can be extracted and used to generate additional positive samples. To identify negative overlapping samples, a membership function encountered fuzzy logic is defined by taking advantage of both local and global information to quantitatively measure the degree, to which each negative sample is an overlapping sample. Then the identified negative overlapping samples are transformed by a transformation matrix that carries the distribution information of all negative samples and shifted to the positive sample region with the center of positive samples. POM is compared with 15 commonly used methods on 14 open-access datasets and experimental results show its superior performance in terms of metrics of Gm, F1 and AUC. © 2023, The Authors. All rights reserved.

关键词： Membership functions

Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ma, Chenglong Li, Zilong Li, Yuanlin Han, Jing Zhang, Junping Zhang, Yi Liu, Jiannan Shan, Hongming Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Department of Oral Maxillofacial Head and Neck Oncology Shanghai Ninth People’ s Hospital Shanghai Jiao Tong University School of Medicine College of Stomatology Shanghai Jiao Tong University National Center for Stomatology National Clinical Research Center for Oral Diseases Shanghai Key Laboratory of Stomatology Shanghai Research Institute of Stomatology Shanghai200011 China School of Cyber Science and Engineering Sichuan University Sichuan Chengdu610065 China

Metal artifacts in computed tomography (CT) images can significantly degrade image quality and impede accurate diagnosis. Supervised metal artifact reduction (MAR) methods, trained using simulated datasets, often struggle to perform well on real clinical CT images due to a substantial domain gap. Although state-of-the-art semi-supervised methods use pseudo ground-truths generated by a prior network to mitigate this issue, their reliance on a fixed prior limits both the quality and quantity of these pseudo ground-truths, introducing confirmation bias and reducing clinical applicability. To address these limitations, we propose a novel radiologist-in-the-loop selftraining framework for MAR, termed RISE-MAR, which can integrate radiologists’ feedback into the semi-supervised learning process, progressively improving the quality and quantity of pseudo ground-truths for enhanced generalization on real clinical CT images. For quality assurance, we introduce a clinical quality assessor model that emulates radiologist evaluations, effectively selecting high-quality pseudo ground-truths for semi-supervised training. For quantity assurance, our self-training framework iteratively generates additional high-quality pseudo ground-truths, expanding the clinical dataset and further improving model generalization. Extensive experimental results on multiple clinical datasets demonstrate the superior generalization performance of our RISE-MAR over state-of-the-art methods, advancing the development of MAR models for practical application. Code is available at https:// ***/Masaaki-75/rise-mar . © 2025, CC BY-NC-SA.

关键词： computerized tomography

Guidelines for public database submission of uncultivated virus genome sequences for taxonomic classification (vol 41, pg 898, 2023)

学校读者我要写书评

暂无评论

NATURE BIOtechnology 2023年第9期41卷 1346-1346页

作者： Adriaenssens, Evelien M. M. Roux, Simon Brister, J. Rodney Karsch-Mizrachi, Ilene Kuhn, Jens H. Varsani, Arvind Yigang, Tong Reyes, Alejandro Lood, Cedric Lefkowitz, Elliot J. Sullivan, Matthew B. B. Edwards, Robert A. A. Simmonds, Peter Rubino, Luisa Sabanadzovic, Sead Krupovic, Mart Dutilh, Bas E. E. Quadram Institute Bioscience Norwich Research Park Rosalind Franklin Road Norwich UK United States Department of Energy Joint Genome Institute Lawrence Berkeley National Laboratory Berkeley CA USA National Center for Biotechnology Information National Library of Medicine National Institutes of Health Bethesda MD USA Integrated Research Facility at Fort Detrick National Institute of Allergy and Infectious Diseases National Institutes of Health Fort Detrick Frederick MD USA The Biodesign Center for Fundamental and Applied Microbiomics Arizona State University Tempe AZ USA Structural Biology Research Unit Department of Clinical Laboratory Sciences University of Cape Town Cape Town South Africa Beijing Advanced Innovation Center for Soft Matter Science and Engineering College of Life Science and Technology Beijing University of Chemical Technology Beijing China Max Planck Tandem Group in Computational Biology Department of Biological Sciences Universidad de los Andes Bogotá Colombia Centre of Microbial and Plant Genetics Department of Microbial and Molecular Systems KU Leuven Leuven Belgium Laboratory of Gene Technology Department of Biosystems KU Leuven Leuven Belgium Institute of Biodiversity Faculty of Biological Sciences Cluster of Excellence Balance of the Microverse Friedrich Schiller University Jena Jena Germany Department of Microbiology University of Alabama at Birmingham Birmingham AL USA Department of Microbiology The Ohio State University Columbus OH USA Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus OH USA Center of Microbiome Science The Ohio State University Columbus OH USA College of Science and Engineering Flinders University Bedford Park South Australia Australia Nuffield Department of Medicine University of Oxford South Parks Road Oxford UK Consiglio Nazionale delle Ricerche Istituto per la Protezione Sostenibile delle Piante Bari Italy Department of Biochemistry Molecular Bio

THE BLESSINGS OF MULTIPLE TREATMENTS AND OUTCOMES IN TREATMENT EFFECT ESTIMATION

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Yong Liu, Mingzhou Yan, Jing Fu, Yanwei Wang, Shouyan Wang, Yizhou Sun, Xinwei Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China Computer Science Department Peking University China School of Data Science Fudan University China Key Laboratory of Computational Neuroscience Brain-Inspired Intelligence China MOE Frontiers Center for Brain Science Fudan University China Zhangjiang Fudan International Innovation Center China Engineering Research Center of AI & Robotics Ministry of Education Fudan University China

Assessing causal effects in the presence of unobserved confounding is a challenging problem. Existing studies leveraged proxy variables or multiple treatments to adjust for the confounding bias. In particular, the latter approach attributes the impact on a single outcome to multiple treatments, allowing estimating latent variables for confounding control. Nevertheless, these methods primarily focus on a single outcome, whereas in many real-world scenarios, there is greater interest in studying the effects on multiple outcomes. Besides, these outcomes are often coupled with multiple treatments. Examples include the intensive care unit (ICU), where health providers evaluate the effectiveness of therapies on multiple health indicators. To accommodate these scenarios, we consider a new setting dubbed as multiple treatments and multiple outcomes. We then show that parallel studies of multiple outcomes involved in this setting can assist each other in causal identification, in the sense that we can exploit other treatments and outcomes as proxies for each treatment effect under study. We proceed with a causal discovery method that can effectively identify such proxies for causal estimation. The utility of our method is demonstrated in synthetic data and sepsis disease. Copyright © 2023, The Authors. All rights reserved.

关键词： Intensive care units

Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Okabe, Ryotaro Cheng, Mouyang Chotrattanapituk, Abhijatmedhi Hung, Nguyen Tuan Fu, Xiang Han, Bowen Wang, Yao Xie, Weiwei Cava, Robert J. Jaakkola, Tommi S. Cheng, Yongqiang Li, Mingda Quantum Measurement Group Massachusetts Institute of Technology CambridgeMA United States Department of Chemistry Massachusetts Institute of Technology CambridgeMA United States Department of Materials Science and Engineering Massachusetts Institute of Technology CambridgeMA United States Center for Computational Science & Engineering Massachusetts Institute of Technology CambridgeMA United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Department of Nuclear Science and Engineering Massachusetts Institute of Technology CambridgeMA United States Frontier Research Institute for Interdisciplinary Sciences Tohoku University Sendai980-8578 Japan Chemical Spectroscopy Group Spectroscopy Section Neutron Scattering Division Oak Ridge National Laboratory Oak RidgeTN United States Department of Chemistry Emory University AtlantaGA United States Department of Chemistry Michigan State University East LansingMI United States Department of Chemistry Princeton University PrincetonNJ United States

Billions of organic molecules are known, but only a tiny fraction of the functional inorganic materials have been discovered, a particularly relevant problem to the community searching for new quantum materials. Recent advancements in machine-learning-based generative models, particularly diffusion models, show great promise for generating new, stable materials. However, integrating geometric patterns into materials generation remains a challenge. Here, we introduce Structural Constraint Integration in the GENerative model (SCIGEN). Our approach can modify any trained generative diffusion model by strategic masking of the denoised structure with a diffused constrained structure prior to each diffusion step to steer the generation toward constrained outputs. Furthermore, we mathematically prove that SCIGEN effectively performs conditional sampling from the original distribution, which is crucial for generating stable constrained materials. We generate eight million compounds using Archimedean lattices as prototype constraints, with over 10% surviving a multi-staged stability pre-screening. High-throughput density functional theory (DFT) on 26,000 survived compounds shows that over 50% passed structural optimization at the DFT level. Since the properties of quantum materials are closely related to geometric patterns, our results indicate that SCIGEN provides a general framework for generating quantum materials candidates. © 2024, CC BY.

关键词： Structural optimization

Quantum Inspired Optimization for Industrial Scale Problems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Banner, William P. Hadiashar, Shima Bab Mazur, Grzegorz Menke, Tim Ziolkowski, Marcin Kennedy, Ken Romero, Jhonathan Cao, Yudong Grover, Jeffrey A. Oliver, William D. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Zapata Computing Inc. 100 Federal St 20th Floor BostonMA02110 United States Department of Computational Methods in Chemistry Jagiellonian University Gronostajowa 2 Kraków30-387 Poland Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Physics Harvard University CambridgeMA02138 United States BMW Group Information Technology Research Center 2 Research Dr. GreenvilleSC29607 United States

Model-based optimization, in concert with conventional black-box methods, can quickly solve large-scale combinatorial problems. Recently, quantum-inspired modeling schemes based on tensor networks have been developed which have the potential to better identify and represent correlations in datasets. Here, we use a quantum-inspired model-based optimization method TN-GEO to assess the efficacy of these quantum-inspired methods when applied to realistic problems. In this case, the problem of interest is the optimization of a realistic assembly line based on BMW's currently utilized manufacturing schedule. Through a comparison of optimization techniques, we found that quantum-inspired model-based optimization, when combined with conventional black-box methods, can find lower-cost solutions in certain contexts. Copyright © 2023, The Authors. All rights reserved.

关键词：

Monitoring Fast Superconducting Qubit Dynamics Using a Neural Network

学校读者我要写书评

暂无评论

Physical Review X 2022年第3期12卷 031017-031017页

作者： G. Koolstra N. Stevenson S. Barzili L. Burns K. Siva S. Greenfield W. Livingston A. Hashim R. K. Naik J. M. Kreikebaum K. P. O’Brien D. I. Santiago J. Dressel I. Siddiqi Quantum Nanoelectronics Laboratory Department of Physics University of California at Berkeley Berkeley California 94720 USA Computational Research Division Lawrence Berkeley National Laboratory Berkeley California 94720 USA Institute for Quantum Studies Chapman University Orange California 92866 USA Schmid College of Science and Technology Chapman University Orange California 92866 USA Department of Physics and Astronomy University of Southern California Los Angeles California 90089 USA Materials Sciences Division Lawrence Berkeley National Laboratory Berkeley California 94720 USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA

Weak measurements of a superconducting qubit produce noisy voltage signals that are weakly correlated with the qubit state. To recover individual quantum trajectories from these noisy signals, traditional methods require slow qubit dynamics and substantial prior information in the form of calibration experiments. Monitoring rapid qubit dynamics, e.g., during quantum gates, requires more complicated methods with increased demand for prior information. Here, we experimentally demonstrate an alternative method for accurately tracking rapidly driven superconducting qubit trajectories that uses a long short-term memory (LSTM) artificial neural network with minimal prior information. Despite few training assumptions, the LSTM produces trajectories that include qubit-readout resonator correlations due to a finite detection bandwidth. In addition to revealing rotated measurement eigenstates and a reduced measurement rate in agreement with theory for a fixed drive, the trained LSTM also correctly reconstructs evolution for an unknown drive with rapid modulation. Our work enables new applications of weak measurements with faster or initially unknown qubit dynamics, such as the diagnosis of coherent errors in quantum gates.

关键词： Machine learning Quantum information processing Quantum measurements Superconducting qubits Weak measurements

学校读者我要写书评

暂无评论

China CDC weekly 2022年第40期4卷 885-889,I0002-I0005页

作者： Yuan Bai Mingda Xu Caifen Liu Mingwang Shen Lin Wang Linwei Tian Suoyi Tan Lei Zhang Petter Holme Xin Lu Eric H.Y.Lau Benjamin J.Cowling Zhanwei Du WHO Collaborating Centre for Infectious Disease Epidemiology and Control School of Public HealthLi Ka Shing Faculty of MedicineThe University of Hong KongHong Kong Special Administrative RegionChina Laboratory of Data Discovery for Health Limited(D24H) Hong Kong Science ParkHong Kong Special Administrative RegionChina China-Australia Joint Research Center for Infectious Diseases School of Public HealthXi’an Jiaotong University Health Science CenterXi’an CityShaanxi ProvinceChina Department of Genetics University of CambridgeCambridge CB23EHUK College of Systems Engineering National University of Defense TechnologyChangsha CityHunan ProvinceChina Department of Computer Science Aalto UniversityEspooFinland Center for Computational Social Science Kobe UniversityKobeJapan

Introduction:Minimizing the importation and exportation risks of coronavirus disease 2019(COVID-19)is a primary concern for sustaining the“Dynamic COVID-zero”strategy in *** estimation is essential for cities to conduct before relaxing border control ***:Informed by the daily number of passengers traveling between 367 prefectures(cities)in China,this study used a stochastic metapopulation model parameterized with COVID-19 epidemic characteristics to estimate the importation and exportation ***:Under the transmission scenario(R0=5.49),this study estimated the cumulative case incidence of Changchun City,Jilin Province as 3,233(95%confidence interval:1,480,4,986)before a lockdown on March 14,2022,which is close to the 3,168 cases reported in real life by March 16,*** a total of 367 prefectures(cities),127(35%)had high exportation risks according to the simulation and could transmit the disease to 50%of all other regions within a period from 17 to 94 *** average time until a new infection arrives in a location in 1 of the 367 prefectures(cities)ranged from 26 to 101 ***:Estimating COVID-19 importation and exportation risks is necessary for preparedness,prevention,and control measures of COVID-19—especially when new variants emerge.

关键词： Export Changchun prevention