检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Qin, Yuzhen El-Gazzar, Ahmed Bassett, Danielle S. Pasqualetti, Fabio Van Gerven, Marcel Donders Institute for Brain Cognition and Behaviour Radboud University Department of Machine Learning and Neural Computing Nijmegen Netherlands University of Pennsylvania The Santa Fe Institute Department of Bioengineering The Department of Electrical & Systems Engineering The Department of Physics & Astronomy The Department of Psychiatry The Department of Neurology United States University of California at Riverside Department of Mechanical Engineering United States

ISBN: (纸本)9798350316339

Epilepsy is one of the most common neurological disorders globally, affecting millions of individuals. Despite significant advancements, the precise mechanisms underlying this condition remain largely unknown, making accurately predicting and preventing epileptic seizures challenging. In this paper, we employ a bistable model, where a stable equilibrium and a stable limit cycle coexist, to describe epileptic dynamics. The equilibrium captures normal steady-state neural activity, while the stable limit cycle signifies seizure-like oscillations. The noise-driven switch from the equilibrium to the limit cycle characterizes the onset of seizures. The differences in the regions of attraction of these two stable states distinguish epileptic brain dynamics from healthy ones. We analytically construct the regions of attraction for both states. Further, using the notion of input-to-state stability with respect to small inputs, we analytically show how the regions of attraction influence the robustness of the system subject to external perturbations. Generalizing the bistable system into coupled networks, we also find the role of network parameters in shaping the regions of attraction. Our findings shed light on the intricate interplay between brain networks and epileptic activity, offering mechanistic insights into potential avenues for more predictable treatments. © 2024 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep learning with Decorrelated Backpropagation

arXiv

引用

arXiv 2024年

作者： Dalm, Sander Offergeld, Joshua Ahmad, Nasir van Gerven, Marcel Department of Machine Learning and Neural Computing Donders Institute for Brain Cognition and Behaviour Thomas van Aquinostraat 4 Nijmegen6525GD Netherlands

The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a significant computational cost and therefore a high carbon footprint. Converging evidence suggests that input decorrelation may speed up deep learning. However, to date, this has not yet translated into substantial improvements in training efficiency in large-scale DNNs. This is mainly caused by the challenge of enforcing fast and stable network-wide decorrelation. Here, we show for the first time that much more efficient training of very deep neural networks using decorrelated backpropagation is feasible. To achieve this goal we made use of a novel algorithm which induces network-wide input decorrelation using minimal computational overhead. By combining this algorithm with careful optimizations, we achieve a more than two-fold speed-up and higher test accuracy compared to backpropagation when training a 18-layer deep residual network. This demonstrates that decorrelation provides exciting prospects for efficient deep learning at scale. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Correlations Are Ruining Your Gradient Descent

arXiv

引用

arXiv 2024年

作者： Ahmad, Nasir Department of Machine Learning and Neural Computing Donders Institute for Brain Cognition and Behaviour Thomas van Aquinostraat 4 Nijmegen6525GD Netherlands

Herein the topics of (natural) gradient descent, data decorrelation, and approximate methods for backpropagation are brought into a common discussion. Natural gradient descent illuminates how gradient vectors, pointing at directions of steepest descent, can be improved by considering the local curvature of loss landscapes. We extend this perspective and show that to fully solve the problem illuminated by natural gradients in neural networks, one must recognise that correlations in the data at any linear transformation, including node responses at every layer of a neural network, cause a non-orthonormal relationship between the model’s parameters. To solve this requires a method for decorrelating inputs at each individual layer of a neural network. We describe a range of methods which have been proposed for decorrelation and whitening of node output, and expand on these to provide a novel method specifically useful for distributed computing and computational neuroscience. Implementing decorrelation within multi-layer neural networks, we can show that not only is training via backpropagation sped up significantly but also existing approximations of backpropagation, which have failed catastrophically in the past, benefit significantly in their accuracy and convergence speed. This has the potential to provide a route forward for approximate gradient descent methods which have previously been discarded, training approaches for analogue and neuromorphic hardware, and potentially insights as to the efficacy and utility of decorrelation processes in the brain. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Noise-based local learning using stochastic magnetic tunnel junctions

引用

Physical Review Applied 2025年第5期23卷 054035-054035页

作者： Kees Koenders Leo Schnitzpan Fabian Kammerbauer Sinan Shu Gerhard Jakob Mathias Kläui Johan H. Mentink Nasir Ahmad Marcel van Gerven Department of Machine Learning and Neural Computing Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen the Netherlands Institute of Physics Johannes Gutenberg University Mainz Mainz 55099 Germany Center for Quantum Spintronics Norwegian University of Science and Technology Trondheim 7491 Norway Department of Physics Radboud University Nijmegen the Netherlands

Brain-inspired learning in physical hardware has enormous potential for rapid learning with minimal energy expenditure. One of the characteristics of biological learning systems is their ability to learn in the presence of various noise sources. Inspired by this observation, we introduce a noise-based learning approach for physical systems implementing multilayer neural networks. Simulation results show that our approach allows for effective learning with a performance approaching that of the conventional backpropagation algorithm, which is effective but has a high energy cost. Using a spintronics hardware implementation, we demonstrate experimentally that learning can be achieved in a small network composed of physical stochastic magnetic tunnel junctions. These results provide a path toward efficient learning in general physical systems that embraces rather than mitigates the noise inherent in physical devices.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Analytical Characterization of Epileptic Dynamics in a Bistable System

Analytical Characterization of Epileptic Dynamics in a Bista...

引用

IEEE Conference on Decision and Control

作者： Yuzhen Qin Ahmed El-Gazzar Danielle S. Bassett Fabio Pasqualetti Marcel Van Gerven Department of Machine Learning and Neural Computing Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherlands Department of Bioengineering the Department of Electrical & Systems Engineering the Department of Physics & Astronomy the Department of Psychiatry and the Department of Neurology University of Pennsylvania and The Santa Fe Institute Department of Mechanical Engineering University of California at Riverside

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

关键词： Neurological diseases Perturbation methods neural activity Limit-cycles Epilepsy Switches Stability analysis Robustness Steady-state Oscillators

来源：评论

学校读者我要写书评

暂无评论

Noise-based Local learning using Stochastic Magnetic Tunnel Junctions

arXiv

引用

arXiv 2024年

作者： Koenders, Kees Schnitzpan, Leo Kammerbauer, Fabian Shu, Sinan Jakob, Gerhard Kläui, Mathias Mentink, Johan H. Ahmad, Nasir van Gerven, Marcel Department of Machine Learning and Neural Computing Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherlands Institute of Physics Johannes Gutenberg University Mainz Mainz55099 Germany Center for Quantum Spintronics Norwegian University of Science and Technology Trondheim7491 Norway Department of Physics Radboud University Nijmegen Netherlands

Brain-inspired learning in physical hardware has enormous potential to learn fast at minimal energy expenditure. One of the characteristics of biological learning systems is their ability to learn in the presence of various noise sources. Inspired by this observation, we introduce a novel noisebased learning approach for physical systems implementing multi-layer neural networks. Simulation results show that our approach allows for effective learning whose performance approaches that of the conventional effective yet energy-costly backpropagation algorithm. Using a spintronics hardware implementation, we demonstrate experimentally that learning can be achieved in a small network composed of physical stochastic magnetic tunnel junctions. These results provide a path towards efficient learning in general physical systems which embraces rather than mitigates the noise inherent in physical devices. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Integration of Longitudinal Noninvasive Diagnostics for Survival Prediction in Immunotherapy Using Deep learning

arXiv

引用

arXiv 2024年

作者： Yeghaian, Melda Bodalal, Zuhir van den Broek, Daan Haanen, John B.A.G. Beets-Tan, Regina G.H. Trebeschi, Stefano van Gerven, Marcel A.J. Department of Machine Learning and Neural Computing Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherlands Department of Radiology Department of Laboratory Medicine Department of Medical Oncology The Netherlands Cancer Institute North Holland Amsterdam1066 CX Netherlands GROW School for Oncology and Developmental Biology Maastricht University Limburg Maastricht6229 ER Netherlands Division of Molecular Oncology and Immunology Oncode Institute Netherlands Cancer Institute Amsterdam Netherlands Department of Medical Oncology Leiden University Medical Center Leiden Netherlands Melanoma Clinic Centre Hospitalier Universitaire Vaudois Lausanne Switzerland Institute of Regional Health Research University of Southern Denmark Odense Denmark

Purpose: Analyzing noninvasive longitudinal and multimodal data using artificial intelligence could potentially transform immunotherapy for cancer patients, paving the way towards precision medicine. Methods: In this study, we integrated pre- and on-treatment blood measurements, prescribed medications and CT-based volumes of organs from a large pan-cancer cohort of 694 patients treated with immunotherapy to predict short and long-term overall survival. By leveraging a combination of recent developments, different variants of our extended multimodal transformer-based simple temporal attention (MMTSimTA) network were trained end-to-end to predict mortality at three, six, nine and twelve months. These models were also compared to baseline methods incorporating intermediate and late fusion based integration methods. Results: The strongest prognostic performance was demonstrated using the extended transformer-based multimodal model with area under the curves (AUCs) of 0.84 ± 0.04, 0.83 ± 0.02, 0.82 ± 0.02, 0.81 ± 0.03 for 3-, 6-, 9-, and 12-month survival prediction, respectively. Conclusion: Our findings suggest that analyzing integrated early treatment data has potential for predicting survival of immunotherapy patients. Integrating complementary noninvasive modalities into a jointly trained model, using our extended transformer-based architecture, demonstrated an improved multimodal prognostic performance, especially in short term survival prediction. © 2024, CC BY.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Self-Awareness for Autonomous Systems

引用

PROCEEDINGS OF THE IEEE 2020年第7期108卷 971-975页

作者： Dutt, Nikil Regazzoni, Carlo S. Rinner, Bernhard Yao, Xin Nikil Dutt (Fellow IEEE) received the Ph.D. degree from the University of Illinois at Urbana–Champaign Champaign IL USA in 1989.""He is currently a Distinguished Professor of computer science (CS) cognitive sciences and electrical engineering and computer sciences (EECS) with the University of California at Irvine Irvine CA USA. He is a coauthor of seven books. His research interests include embedded systems electronic design automation (EDA) computer architecture distributed systems healthcare Internet of Things (IoT) and brain-inspired architectures and computing.""Dr. Dutt is a Fellow of ACM. He was a recipient of the IFIP Silver Core Award. He has received numerous best paper awards. He serves as the Steering Committee Chair of the IEEE/ACM Embedded Systems Week (ESWEEK). He is also on the steering organizing and program committees of several premier EDA and embedded system design conferences and workshops. He has served on the Editorial Boards for the IEEE Transactions on Very Large Scale Integration (VLSI) Systems and the ACM Transactions on Embedded Computing Systems and also previously served as the Editor-in-Chief (EiC) for the ACM Transactions on Design Automation of Electronic Systems. He served on the Advisory Boards of the IEEE Embedded Systems Letters the ACM Special Interest Group on Embedded Systems the ACM Special Interest Group on Design Automationt and the ACM Transactions on Embedded Computing Systems. Carlo S. Regazzoni (Senior Member IEEE) received the M.S. and Ph.D. degrees in electronic and telecommunications engineering from the University of Genoa Genoa Italy in 1987 and 1992 respectively.""He is currently a Full Professor of cognitive telecommunications systems with the Department of Electrical Electronics and Telecommunication Engineering and Naval Architecture (DITEN) University of Genoa and a Co-Ordinator of the Joint Doctorate on Interactive and Cognitive Environments (JDICE) international Ph.D. course started initially as EU Erasmus Mundus Project and

Autonomous systems are able to make decisions and potentially take actions without direct human intervention, which requires some knowledge about the system and its environment as well as goal-oriented reasoning. In computer systems, one can derive such behavior from the concept of a rational agent with autonomy (“control over its own actions”), reactivity (“react to events from the environment”), proactivity (“act on its own initiative”), and sociality (“interact with other agents”) as fundamental properties \n[1]\n. Autonomous systems will undoubtedly pervade into our everyday lives, and we will find them in a variety of domains and applications including robotics, transportation, health care, communications, and entertainment to name a few. \nThe articles in this month’s special issue cover concepts and fundamentals, architectures and techniques, and applications and case studies in the exciting area of self-awareness in autonomous systems.

关键词： Special issues and sections Autonomous systems Self-aware Robot sensing systems Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Multivariate machine learning Methods for Fusing Multimodal Functional Neuroimaging Data

Multivariate Machine Learning Methods for Fusing Multimodal ...

引用

作者： Dahne, Sven Bieszmann, Felix Samek, Wojciech Haufe, Stefan Goltz, Dominique Gundlach, Christopher Villringer, Arno Fazli, Siamac Muller, Klaus-Robert Machine Learning Group Department of Computer Science Berlin Institute of Technology Berlin10623 Germany Amazon Berlin10178 Germany Machine Learning Group Department of Video Coding and Analytics Fraunhofer Heinrich Hertz Institute Berlin10587 Germany Laboratory for Intelligent Imaging and Neural Computing Columbia University New YorkNY10027 United States Institute of Psychology University of Leipzig Leipzig04109 Germany Department for Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig04103 Germany Mind-Brain Institute Charite Universitätsmedizin Berlin Humboldt-University Berlin10117 Germany Clinic for Cognitive Neurology University of Leipzig Leipzig04109 Germany Department of Brain and Cognitive Engineering Korea University Seoul136-713 Korea Republic of

Multimodal data are ubiquitous in engineering, communications, robotics, computer vision, or more generally speaking in industry and the sciences. All disciplines have developed their respective sets of analytic tools to fuse the information that is available in all measured modalities. In this paper, we provide a review of classical as well as recent machine learning methods (specifically factor models) for fusing information from functional neuroimaging techniques such as: LFP, EEG, MEG, fNIRS, and fMRI. Early and late fusion scenarios are distinguished, and appropriate factor models for the respective scenarios are presented along with example applications from selected multimodal neuroimaging studies. Further emphasis is given to the interpretability of the resulting model parameters, in particular by highlighting how factor models relate to physical models needed for source localization. The methods we discuss allow for the extraction of information from neural data, which ultimately contributes to 1) better neuroscientific understanding;2) enhance diagnostic performance;and 3) discover neural signals of interest that correlate maximally with a given cognitive paradigm. While we clearly study the multimodal functional neuroimaging challenge, the discussed machine learning techniques have a wide applicability, i.e., in general data fusion, and may thus be informative to the general interested reader. © 2015 IEEE.

关键词： Neurophysiology

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：