检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Larchenko, Maria A. Osinenko, P. Yaremenko, G. Palyulin, V.V. Center for Computational and Data-intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia

Optimization of first-passage times is required in applications ranging from nanobots navigation to market trading. In such settings, one often encounters unevenly distributed noise levels across the environment. We extensively study how a learning agent fares in 1- and 2- dimensional heated gridworlds with an uneven temperature distribution. The results show certain bias effects in agents trained via simple tabular Q-learning, SARSA, Expected SARSA and Double Q-learning. While high learning rate prevents exploration of regions with higher temperature, low enough rate increases the presence of agents in such regions. The discovered peculiarities and biases of temporal-difference-based reinforcement learning methods should be taken into account in real-world physical applications and agent design. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Bayesian sparsification of deep C-valued networks 37

Bayesian sparsification of deep C-valued networks

引用

37th International Conference on Machine Learning, ICML 2020

作者： Nazarov, Ivan Burnaev, Evgeny Centre for Data Intensive Sciecne and Engineering Skolkovo Insitiute of Science and Technology Msocow Russia

ISBN: (纸本)9781713821120

With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural representation in the complex domain. To this end we extend Sparse Variational Dropout to complex-valued neural networks and verify the proposed Bayesian technique by conducting a large numerical study of the performance-compression trade-off of C-valued networks on two tasks: image recognition on MNIST-like and CIFAR10 datasets and music transcription on MusicNet. We replicate the state-of-the-art result by Trabelsi et al. (2018) on MusicNet with a complex-valued network compressed by 50 − 100× at a small performance penalty. © 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

LightPRA: A Lightweight Temporal Convolutional Network for Automatic Physical Rehabilitation Exercise Assessment

引用

Computers in Biology and Medicine 2024年 173卷 108382-108382页

作者： Sardari, Sara Sharifzadeh, Sara Daneshkhah, Alireza Loke, Seng W. Palade, Vasile Duncan, Michael J. Nakisa, Bahareh Research Centre for Computational Science and Mathematical Modelling Coventry University Coventry United Kingdom School of Information Technology Faculty of Science Engineering and Built Environment Deakin University Geelong Vic Australia Department of Computer Science Swansea University Swansea United Kingdom School of Mathematics and Data Science Emirates Aviation University Dubai United Arab Emirates Centre for Sport Exercise and Life Sciences Coventry University Coventry United Kingdom

Research evidence shows that physical rehabilitation exercises prescribed by medical experts can assist in restoring physical function, improving life quality, and promoting independence for physically disabled individuals. In response to the absence of immediate expert feedback on performed actions, developing a Human Action Evaluation (HAE) system emerges as a valuable automated solution, addressing the need for accurate assessment of exercises and guidance during physical rehabilitation. Previous HAE systems developed for the rehabilitation exercises have focused on developing models that utilize skeleton data as input to compute a quality score for each action performed by the patient. However, existing studies have focused on improving scoring performance while often overlooking computational efficiency. In this research, we propose LightPRA (Light Physical Rehabilitation Assessment) system, an innovative architectural solution based on a Temporal Convolutional Network (TCN), which harnesses the capabilities of dilated causal Convolutional Neural Networks (CNNs). This approach efficiently captures complex temporal features and characteristics of the skeleton data with lower computational complexity, making it suitable for real-time feedback provided on resource-constrained devices such as Internet of Things (IoT) devices and Edge computing frameworks. Through empirical analysis performed on the University of Idaho-Physical Rehabilitation Movement data (UI-PRMD) and KInematic assessment of MOvement for remote monitoring of physical REhabilitation (KIMORE) datasets, our proposed LightPRA model demonstrates superior performance over several state-of-the-art approaches such as Spatial–Temporal Graph Convolutional Network (STGCN) and Long Short-Term Memory (LSTM)-based models in scoring human activity performance, while exhibiting lower computational cost and complexity. © 2024 The Authors

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Conceptual Method of Temperature Sensation in Bionic Hand by Extraordinary Perceptual Phenomenon

引用

Journal of Bionic engineering 2021年第6期18卷 1344-1357页

作者： Saeed Bahrami Moqadam Ahamd Saleh Asheghabadi Farzaneh Norouzi Hamed Jafarzadeh Ali Khosroabadi AfshinAlagheband Ghazal Bangash Negar Morovatdar Jing Xu State Key Laboratory of Tribology Department of Mechanical EngineeringTsinghua UniversityBeijing100084China Medical University of Mashhad 13131–99137MashhadIran Center for Computational and Data Intensive Science and Engineering(CDISE) Skolkovo Institute of Science and Technology(Skoltech)Moscow121205Russia Department of Mechanical Engineering Ferdowsi UniversityMashhad***Iran Department of Electrical Engineering Ferdowsi UniversityMashhad***Iran Department of Computer Engineering Ferdowsi UniversityMashhad***Iran Clinical Research Unit Imam Reza HospitalMashhad University of Medical Sciences13131–99137MashhadIran

Lack of temperature sensation of myoelectric prosthetic hand limits the daily activities of *** this end,a noninvasive temperature sensation method is proposed to train amputees to sense temperature with psychophysical sensory *** this study,22 healthy participants took part besides 5 amputee *** duration time of the study was 31 days with five test steps according to the Leitner *** adjustable temperature mug and a Peltier were used to change the temperature of the water/phantom digits to induce temperature to ***,to isolate the surroundings and show colors,a Virtual Reality(VR)glass was *** statistical results conducted are based on the response of participants with questionnaire *** Chi-square tests,it is concluded that participants answer the experiment significantly correctly using the Leitner technique(P value<0.05).Also,by applying the“Repeated Measures ANOVA”,it is noticed that the time of numbness felt by participants had significant(P value<0.001)*** could remember lowest and highest temperatures significantly better than other temperatures(P value<0.001);furthermore,the well-trained amputee participant practically using the prosthesis with 72.58%could identify object’s temperature with only once time experimenting the color temperature.

关键词： Temperature perceptions Leitner learning technique Classical conditioning Psychophysical sensory substitution Extraordinary perceptual phenomenon Bionic hand prosthesis

来源：评论

学校读者我要写书评

暂无评论

Machine Learning with Physics Knowledge for Prediction: A Survey

arXiv

引用

arXiv 2024年

作者： Watson, Joe Song, Chen Weeger, Oliver Gruner, Theo Le, An T. Hansel, Kay Hendawy, Ahmed Arenz, Oleg Trojak, Will Cranmer, Miles D’Eramo, Carlo Bülow, Fabian Goyal, Tanmay Peters, Jan Hoffman, Martin W. Department of Computer Science Technical University of Darmstadt Germany Germany Germany Center for Artificial Intelligence and Data Science University of Würzburg Germany Centre for Cognitive Science Technical University of Darmstadt Germany ABB Corporate Research Center Mannheim Germany Department of Mechanical Engineering Technical University of Darmstadt Germany IBM Research UKI United Kingdom Data Intensive Science University of Cambridge United Kingdom

This survey examines the broad suite of methods and models for combining machine learning with physics knowledge for prediction and forecast, with a focus on partial differential equations. These methods have attracted significant interest due to their potential impact on advancing scientific research and industrial practices by improving predictive models with small- or large-scale datasets and expressive predictive models with useful inductive biases. The survey has two parts. The first considers incorporating physics knowledge on an architectural level through objective functions, structured predictive models, and data augmentation. The second considers data as physics knowledge, which motivates looking at multi-task, meta, and contextual learning as an alternative approach to incorporating physics knowledge in a data-driven fashion. Finally, we also provide an industrial perspective on the application of these methods and a survey of the open-source ecosystem for physics-informed machine learning. Copyright © 2024, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Tiny noise, big mistakes: adversarial perturbations induce errors in brain–computer interface spellers

引用

National science Review 2021年第4期8卷 78-90页

作者： Xiao Zhang Dongrui Wu Lieyun Ding Hanbin Luo Chin-Teng Lin Tzyy-Ping Jung Ricardo Chavarriaga Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Civil Engineering and Mechanics Huazhong University of Science and Technology Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Swartz Center for Computational Neuroscience Institute for Neural ComputationUniversity of California San Diego Center for Advanced Neurological Engineering Institute of Engineering in Medicine University of California San Diego ZHAW Data Lab Zürich University of Applied Sciences

An electroencephalogram(EEG)-based brain–computer interface(BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g. amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a *** studies so far focused on making EEG-based BCI spellers faster and more reliable; however, few have considered their security. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e. they can be severely attacked by adversarial perturbations,which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before.

关键词： electroencephalogram brain-computer interfaces BCI spellers adversarial examples

来源：评论

学校读者我要写书评

暂无评论

A THEORY OF INITIALISATION’S IMPACT ON SPECIALISATION

arXiv

引用

arXiv 2025年

作者： Jarvis, Devon Lee, Sebastian Dominé, Clémentine Carla Juliette Saxe, Andrew M. Mannelli, Stefano Sarao School of Computer Science and Applied Mathematics University of the Witwatersrand South Africa Center for Computational Neuroscience Flatiron Institute Simons Foundation Gatsby Computational Neuroscience Unit Sainsbury Wellcome Centre UCL United Kingdom Data Science and AI Computer Science and Engineering Chalmers University of Technology University of Gothenburg Sweden Machine Intelligence and Neural Discovery Institute University of the Witwatersrand South Africa CIFAR Azrieli Global Scholar CIFAR

Prior work has demonstrated a consistent tendency in neural networks engaged in continual learning tasks, wherein intermediate task similarity results in the highest levels of catastrophic interference. This phenomenon is attributed to the network’s tendency to reuse learned features across tasks. However, this explanation heavily relies on the premise that neuron specialisation occurs, i.e. the emergence of localised representations. Our investigation challenges the validity of this assumption. Using theoretical frameworks for the analysis of neural networks, we show a strong dependence of specialisation on the initial condition. More precisely, we show that weight imbalance and high weight entropy can favour specialised solutions. We then apply these insights in the context of continual learning, first showing the emergence of a monotonic relation between task-similarity and forgetting in non-specialised networks. Finally, we show that specialization by weight imbalance is beneficial on the commonly employed elastic weight consolidation regularisation technique. Copyright © 2025, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Benchmarks of Cuda-Based GMRES Solver for Toeplitz and Hankel Matrices and Applications to Topology Optimization of Photonic Components

引用

computational Mathematics and Modeling 2021年第4期32卷 438-452页

作者： Minin, Iu. B. Matveev, S.A. Fedorov, M.V. Zacharov, I.E. Rykovanov, S.G. Skoltech Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow Russian Federation Fryazino Branch of Kotel’nikov Institute of Radio-Engineering and Electronics of Russian Academy of Sciences Moscow Fryazino Russian Federation Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russian Federation Marchuk Institute of Numerical Mathematics Russian Academy of Sciences Moscow Russian Federation Sirius University of Science and Technology Krasnodar Krai Sochi Russian Federation

Generalized Minimal Residual Method (GMRES) was benchmarked on many types of GPUs for solving linear systems based on dense and sparse matrices. However, there are still no GMRES implementation benchmarks on Tesla V100 compared to GTX 1080 Ti ones or even for Toeplitz-like matrices. The introduced software consists of a Python module and a C++ library which enable to manage streams for concurrent computations of separated linear systems on a GPU (and GPUs). The GMRES solver is parallelized for running on a NVIDIA GPGPU accelerator. The parallelization efficiency is explored when GMRES is applied to solve (Helmholtz equation) linear systems based on the use of Green’s Function Integral Equation Method (GFIEM) for computing electric field distribution in the design domain. The proposed implementation shew the maximal speedup of 55 (t¯=0.017s) and of 125 (t¯=0.77s) for 1024 × 1024 (on GTX 1080 Ti) and 8192 × 8192 (on Tesla V100) dense Toeplitz matrices generated from GFIEM. 1024 × 1024 resolution provides accuracy 6.1% that can be acceptable according to testing and demonstrating on gradient computations and topology optimization. We open up possibilities for robust topology optimization of passive photonic integrated components. That has the advantage, e. g., of faster and more accurate designing photonic components on a PC without a supercomputer. © 2022, Springer science+Business Media, LLC, part of Springer Nature.

关键词： CUDA C++ GMRES GPU Helmholtz equation parallelization performance Python module Toeplitz-like matrix topology optimization

来源：评论

学校读者我要写书评

暂无评论

High-Performance computational Approach for Inverse Design of Passive Photonic Components

High-Performance Computational Approach for Inverse Design o...

引用

2022 Laser Applications Conference, LAC 2022

作者： Minin, Iurii Matveev, Sergey Skoltech Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Bolshoy Boulevard 30 bld.1 Moscow121205 Russia Fryazino Branch of Kotel’nikov Institute of Radio-Engineering and Electronics of RAS Vvedenskiy sq. 1 Moscow Region Fryazino141190 Russia Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Leninskie Gory 1-52 2nd educational building 6th floor room 663 Moscow119991 Russia Marchuk Institute of Numerical Mathematics RAS Moscow Russia

We propose novel approach for high-performance computations of electric field distributions which uses Green’s Function Integral Equation Method, memcopy-free GMRES, fast (FFT-based) matvecs and can work 10 times fas... 详细信息

ISBN: (纸本)9781957171203

关键词： Integral equations

来源：评论

学校读者我要写书评

暂无评论

Detection of ChatGPT Fake science with the xFakeSci Learning Algorithm

arXiv

引用

arXiv 2023年

作者： Hamed, Ahmed Abdeen Wu, Xindong Complex Adaptive Systems and Computational Intelligence Laboratory State University of New York at Binghamton BinghamtonNY13902 United States Sano Centre for Computational Medicine Clinical Data Science Cracow30-072 Poland Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230009 China China Electronics Data Industry Group Shenzhen518057 China

Generative AI tools exemplified by ChatGPT are becoming a new reality. This study is motivated by the premise that "AI generated content may exhibit a distinctive behavior that can be separated from scientific articles". In this study, we show how articles can be generated using means of prompt engineering for various diseases and conditions. We then show how we tested this premise in two phases and prove its validity. Subsequently, we introduce xFakeSci, a novel learning algorithm, that is capable of distinguishing ChatGPT-generated articles from publications produced by scientists. The algorithm is trained using network models driven from both sources. To mitigate overfitting issues, we incorporated a calibration step that is built upon data-driven heuristics, including proximity and ratios. Specifically, from a total of a 3952 fake articles for three different medical conditions, the algorithm was trained using only 100 articles, but calibrated using folds of 100 articles. As for the classification step, it was performed using 300 articles per condition. The actual label steps took place against an equal mix of 50 generated articles and 50 authentic PubMed abstracts. The testing also spanned publication periods from 2010 to 2024 and encompassed research on three distinct diseases: cancer, depression, and Alzheimer’s. Further, we evaluated the accuracy of the xFakeSci algorithm against some of the classical data mining algorithms (e.g., Support Vector Machines, Regression, and Naive Bayes). The xFakeSci algorithm achieved F1 scores ranging from 80% to 94%, outperforming common data mining algorithms, which scored F1 values between 38% and 52%. We attribute the noticeable difference to the introduction of calibration and a proximity distance heuristic, which underscores this promising performance. Indeed, the prediction of fake science generated by ChatGPT presents a considerable challenge. Nonetheless, the introduction of the xFakeSci algorithm is a significant st

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：