检索结果-内蒙古大学图书馆

FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jena, Rohit Chaudhari, Pratik Gee, James C. Computer and Information Science University of Pennsylvania United States Electrical and Systems Engineering University of Pennsylvania United States Radiology Perelman School of Medicine University of Pennsylvania United States Penn Image Computing and Science Laboratory University of Pennsylvania United States

The paper proposes FireANTs, the first multi-scale Adaptive Riemannian Optimization algorithm for dense diffeomorphic image matching. One of the most critical and understudied aspects of diffeomorphic image matching algorithms are its highly ill-conditioned nature. We quantitatively capture the extent of ill-conditioning in a typical MRI matching task, motivating the need for an adaptive optimization algorithm for diffeomorphic matching. To this end, FireANTs generalizes the concept of momentum and adaptive estimates of the Hessian to mitigate this ill-conditioning in the non-Euclidean space of diffeomorphisms. Unlike common non-Euclidean manifolds, we also formalize considerations for multi-scale optimization of diffeomorphisms. Our rigorous mathematical results and operational contributions lead to a state-of-the-art dense matching algorithm that can be applied to generic image data with remarkable accuracy and robustness. We demonstrate consistent improvements in image matching performance across a spectrum of community-standard medical and biological correspondence matching challenges spanning a wide variety of image modalities, anatomies, resolutions, acquisition protocols, and preprocessing pipelines. This improvement is supplemented by from 300× up to 3200× speedup over existing state-of-the-art algorithms. For the first time, we perform diffeomorphic matching of sub-micron mouse cortex volumes at native resolution. Our fast implementation also enables hyperparameter studies that were intractable with existing correspondence matching algorithms. © 2024, CC BY.

关键词： Neuroimaging

Mechanical Design with Experimental Verification of a Lightweight Exoskeleton Chair

学校读者我要写书评

暂无评论

Journal of Bionic engineering 2021年第2期18卷 319-332页

作者： Zihao Du Zefeng Yan Tiantian Huang Ou Bai Qin Huang Bin Han State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Human Cyber-Physical Systems Laboratory Department of Electrical and Computer EngineeringFlorida International UniversityMiami 33174USA Department of Rehabilitation Medicine Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China

In this study,a human-chair model was developed as the basis for a wearable-chair design.A prototype chair,HUST-EC,based on the model was fabricated and *** the optimization under the golden divisional method,an optimized simulation of the operating mode with the lowest chair height was implemented.A novel multi-link support structure has been established with parameters optimized using Matlab *** stress analysis of the solid models was conducted to ensure the adequate support from the designed chair for the *** subjects participated in the evaluation experiment,who performed both static tasks and dynamic *** experimental results consisted of subjective evaluation and objective *** experimental data demonstrate that(1)the HUST-EC can effectively reduce the activation level of related muscles at a variety of tasks;(2)the plantar pressure was reduced by 54%–67%;(3)the angle between the upper body and the vertical axis was reduced by 59%–77%;(4)the subjective scores for chair comfortability,portability,and stability were all higher than *** results further revealed that the designed chair can reduce the musculoskeletal burden and may improve work efficiency.

关键词： exoskeleton wearable chair bionic robot mechanism design ergonomics

Robust characterization of photonic integrated circuits

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Jiajia Xu, Xingyuan Zhang, Haoran Zeng, Xuecheng Bai, Yunping Lowery, Arthur J. Xu, Kun State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing100876 China Electro-Photonics Laboratory Department of Electrical and Computer Systems Engineering Monash University ClaytonVIC3800 Australia

Photonic integrated circuits (PICs) offer ultra-broad optical bandwidths that enable unprecedented data throughputs for signal processing applications. Dynamic reconfigurability enables compensation of fabrication flaws and fluctuating external environments, tuning for adaptive equalization and training of optical neural networks. The initial step in PIC reconfiguration entails measuring its dynamic performance, often described by its frequency response. While measuring the amplitude response is straightforward, e.g. using a tunable laser and optical power meter, measuring the phase response presents challenges due to various factors, including phase variations in test connections and instrumentation limitations. To address these challenges, a universal and robust characterization technique is proposed, which uses an on-chip reference path coupled to the signal processing core (SPC), with a delay larger or smaller than the total delay across the signal processing paths. A Fourier transform of the chip's power response reveals the SPC's impulse response. The method is more robust against low reference-path power and imprecise delays. Experiments using a finite-impulse-response (FIR) structure demonstrate rapid SPC training, overcoming thermal crosstalk and device imperfections. This approach offers a promising solution for PIC characterization, facilitating expedited physical parameter training for advanced applications in communications and optical neural networks. Copyright © 2024, The Authors. All rights reserved.

关键词： Photonic integrated circuits

Action Recognition via Graph Convolutional Networks for the Assisted Living of the Elderly

学校读者我要写书评

暂无评论

Action Recognition via Graph Convolutional Networks for the ...

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Zois Tsakiris Lazaros Tsochatzidis Ioannis Pratikakis Dimitrios Menychtas Nikolaos Aggelousis Department of Electrical and Computer Engineering Visual Computing Group Democritus University of Thrace Xanthi Greece Department of Physical Education and Sports Science Biomechanics Laboratory Democritus University of Thrace Komotini Greece

ISBN: (数字)9798350308921

ISBN: (纸本)9798350308938

Automated monitoring systems can play a crucial role in the effective assisted living of the elderly. Such systems aim to detect specific actions or activities of the individual which may indicate discomfort, pain or danger. Towards this end, we employ a skeleton-based representation for the human body, as a graph of interconnected nodes, that can be used as the means of meaningful spatial-temporal information of an action. In this paper, a novel methodology for human action recognition is proposed in the context of Graph Convolutional Networks that, along with the conventional full-body human graph, utilizes an arm-specific graph representation to better capture the fine-grained motion of the arms. For experimental evaluation, a new dataset is created that comprises a variety of actions, performed by multiple elderly individuals, specifically for the purpose of monitoring everyday life activities. Additionally, experimentation is extended to a well-established large dataset, namely NTU RGB+D 120, focusing on the actions that correspond to medical conditions. Experimental results demonstrate the effectiveness of our combined approach, compared to the single graph approach, in terms of recognition accuracy.

关键词： Medical conditions Graph convolutional networks Pain Conferences Focusing Nanoscale devices Assisted living

Embracing Irregular Parallelism in HPC with YGM

学校读者我要写书评

暂无评论

Embracing Irregular Parallelism in HPC with YGM

Supercomputing Conference

作者： Trevor Steil Tahsin Reza Benjamin W. Priest Roger Pearce Lawrence Livermore National Laboratory (LLNL) Center for Applied Scientific Computing (CASC) Livermore CA USA Department of Electrical and Computer Engineering University of Waterloo Waterloo Ontario Canada

YGM is a general-purpose asynchronous distributed computing library for C++/MPI, designed to handle the irregular data access patterns and small messages of graph algorithms and data science applications. It uses data serialization to give an easily usable active message interface and message aggregation to maximize application throughput. Our design philosophy makes a tradeoff that increases network bandwidth utilization at the cost of added latency. We provide a suite of benchmarks showcasing YGM's performance. Compared to similar distributed active message benchmark implementations that do not provide message buffering, we are able to achieve over 10x throughput on thousands of cores at a latency cost that can be as small as 2x or as large as 100x, depending on the machine being used. For applications that can be written to be latency-tolerant, this represents a significant potential performance improvement through using YGM.

关键词：

Copula Guided Parallel Gibbs Sampling for Nonparametric and Coherent Topic Discovery (Extended Abstract) 39

学校读者我要写书评

暂无评论

Copula Guided Parallel Gibbs Sampling for Nonparametric and ...

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Lin, Lihui Rao, Yanghui Xie, Haoran Lau, Raymond Y. K. Yin, Jian Wang, Fu Lee Li, Qing Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Lingnan University Department of Computing and Decision Sciences New Territories Hong Kong City University of Hong Kong Department of Information Systems Kowloon Hong Kong Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Hong Kong Metropolitan University School of Science and Technology Kowloon Hong Kong The Hong Kong Polytechnic University Department of Computing Kowloon Hong Kong

ISBN: (纸本)9798350322279

In terms of the generative process, the Gamma-Gamma-Poisson Process (G2PP) is equivalent to the nonparametric topic model of Hierarchical Dirichlet Process (HDP). Considering the high computational cost of estimating parameters in HDP, a parallel G2PP was developed to generate topics efficiently via multi-threading. Unfortunately, the above model needs to predefine the number of topics. To address this issue, we first propose a Topic Self-Adaptive Model (TSAM) for nonparametric and parallel topic discovery. In TSAM, a monitor-executor mechanism is developed to manage the global topic information using a hierarchical structure of threads. Based on the apparatus of copulas, we further extend our TSAM to TSAMcop for coherent topic modeling by exploiting a copula guided parallel Gibbs sampling algorithm. Extensive experiments validate the effectiveness of both TSAM and TSAMcop. © 2023 IEEE.

关键词： Information management

Convex Ternary Quartics Are SOS-Convex

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ahmadi, Amir Ali Blekherman, Grigoriy Parrilo, Pablo A. The Department of Operations Research and Financial Engineering Princeton University United States The School of Mathematics The Georgia Institute of Technology United States The Laboratory for Information and Decision Systems The Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States

We show that if a ternary quartic form is convex, then it must be sos-convex;i.e, if the Hessian H(x) of a ternary quartic form is positive semidefinite for all x, then the biquadratic form yT H(x)y in the variables x:= (x1, x2, x3)T and y:= (y1, y2, y3)T must be a sum of squares. This result is in a meaningful sense the "convex analogue" of Hilbert’s celebrated theorem on ternary quartics. We show that exploiting the structure of the Hessian matrix is crucial in any possible proof of this result by presenting an explicit example of a biquadratic form b(x, y) that is symmetric in x and y, nonnegative, but not a sum of squares. © 2024, CC BY.

关键词： Matrix algebra

A General Framework for Clustering and Distribution Matching with Bandit Feedback

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y.F. Scarlett, Jonathan Descartes Program CNRS@CREATE 138602 Singapore Department of Information Systems and Analytics School of Computing National University of Singapore 119077 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore 119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank–Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ *** Codes 68T05 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

Adam-family methods for nonsmooth optimization with convergence guarantees

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2024年第1期25卷 2398-2450页

作者： Nachuan Xiao Xiaoyin Hu Xin Liu Kim-Chuan Toh Institute of Operations Research and Analytics National University of Singapore Singapore School of Computer and Computing Science Hangzhou City University Hangzhou China State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Department of Mathematics and Institute of Operations Research and Analytics National University of Singapore Singapore

In this paper, we present a comprehensive study on the convergence properties of Adam-family methods for nonsmooth optimization, especially in the training of nonsmooth neural networks. We introduce a novel two-timescale framework that adopts a two-timescale updating scheme, and prove its convergence properties under mild assumptions. Our proposed framework encompasses various popular Adam-family methods, providing convergence guarantees for these methods in training nonsmooth neural networks. Furthermore, we develop stochastic subgradient methods that incorporate gradient clipping techniques for training nonsmooth neural networks with heavy-tailed noise. Through our framework, we show that our proposed methods converge even when the evaluation noises are only assumed to be integrable. Extensive numerical experiments demonstrate the high efficiency and robustness of our proposed methods.

关键词： nonsmooth optimization stochastic subgradient methods Adam nonconvex optimization gradient clipping