检索结果-内蒙古大学图书馆

26th International Conference on Information Fusion, FUSION 2023

作者： Liu, Yi Li, Xi Yang, Le Mihaylova, Lyudmila Xue, Yanbo University of Canterbury Department of Electrical and Computer Engineering Christchurch New Zealand National University of Defense Technology State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems Changsha China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Career Science Lab Beijing China

ISBN: (纸本)9798890344854

The quotient of two multivariate Gaussian densities can be written as an unnormalized Gaussian density, which has been applied in some recently developed multiple-model fixed-interval smoothing algorithms. However, this expression is invalid if instead of being positive definite, the covariance of the unnormalized Gaussian density is indefinite (i.e., it has both positive and negative eigenvalues) or undefined (i.e., computing it requires inverting a singular matrix). This paper considers approximating the quotient of two Gaussian densities in this case using two different approaches to mitigate the caused numerical problems. The first approach directly replaces the indefinite covariance of the unnormalized Gaussian density with a positive definite matrix nearest to it. The second approach computes the approximation through solving, using the natural gradient, an optimization problem with a Kullback-Leibler divergence-based cost function. This paper illustrates the application of the theoretical results by incorporating them into an existing smoothing method for jump Markov systems and utilizing the obtained smoothers to track a maneuvering target. © 2023 International Society of Information Fusion.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Low-Complexity Hardware Architecture of an H.264-Based Video Encoder for FPGAs

Low-Complexity Hardware Architecture of an H.264-Based Video...

引用

computer Science, computer engineering, & Applied Computing (CSCE), Congress in

作者： Azam Tayyebi Darrin Hanna Bryant Jones Department of Electrical and Computer Engineering Oakland University Rochester USA Intrepid Control Systems Troy USA

In this paper, we present an architecture for a scalable, efficient, realtime intra H.264 video encoder implemented on an FPGA. Our architecture was designed to achieve a through-put of up to 2.3 Gbit/s using a parallel and pipelined architecture described in VHDL. All modules in the architecture are optimized to utilize minimum hardware area. A parameterized encoding system and flexible architecture is proposed to provide the ability to achieve different compression ratios ranging from 1.4 to 2 with varying size and power requirements. As a baseline, with no compression, the encoder required hardware resources equivalent to 18K logic gates. This work experimented with compression ratios up to 2 which required an equivalent of 31K logic gates. The encoder performs at frequency ranges of 159–183 MHz.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement-Learning-Based Risk-Sensitive Optimal Feedback Mechanisms of Biological Motor control

Reinforcement-Learning-Based Risk-Sensitive Optimal Feedback...

引用

IEEE Conference on Decision and control

作者： Leilei Cui Bo Pang Zhong-Ping Jiang Department of Electrical and Computer Engineering Control and Networks Lab Tandon School of Engineering New York University Brooklyn NY USA

Risk sensitivity is a fundamental aspect of biological motor control that accounts for both the expectation and variability of movement cost in the face of uncertainty. However, most computational models of biological motor control rely on model-based risk-sensitive optimal control, which requires an accurate internal representation in the central neural system to predict the outcomes of motor commands. In reality, the dynamics of human-environment interaction is too complex to be accurately modeled, and noise further complicates system identification. To address this issue, this paper proposes a novel risk-sensitive computational mechanism for biological motor control based on reinforcement learning (RL) and adaptive dynamic programming (ADP). The proposed ADP-based mechanism suggests that humans can directly learn an approximation of the risk-sensitive optimal feedback controller from noisy sensory data without the need for system identification. Numerical validation of the proposed mechanism is conducted on the arm-reaching task under divergent force field. The preliminary computational results align with the experimental observations from the past literature of computational neuroscience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Character Recognition of Vedic Sanskrit using Deep Learning Algorithms 3

Character Recognition of Vedic Sanskrit using Deep Learning ...

引用

3rd IEEE International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2022

作者： Pandey, Mrinal Pandey, Rashmikiran Nazarov, Alexey Moscow Institute of Physics and Technology Department of Radio Engineering and Cybernetics Moscow Russia Federal Research Center Computer Science and Control Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9781665462006

One of the applications of deep learning is deciphering the unscripted text over the walls and pillars of historical monuments is the major source of information extraction. This information gives us an idea about the art and the culture of that respective era. In this paper we proposed a model for digital recognition of textual characters written in Sanskrit language using the 4-fold Convolutional Neural Network (CNN) architecture. At the first stage we remove the noise and subsequently segmentation of characters from the input image is performed, later we convert the image into binary image format by the help of image processing techniques. The research is performed over the Devanagari script which was developed during 1st to the 4th century CE and is common to many languages from the Indian subcontinent. © 2022 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Simple and Optimal Sublinear Algorithms for Mean Estimation

arXiv

引用

arXiv 2024年

作者： Bertolotti, Beatrice Russo, Matteo Schwiegelshohn, Chris Shyam, Sudarshan Department of Computer Science Aarhus University Åbogade 34 Aarhus N8200 Denmark Department of Computer Control Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy

We study the sublinear multivariate mean estimation problem in d-dimensional Euclidean space. Specifically, we aim to find the mean µ of a ground point set A, which minimizes the sum of squared Euclidean distances of the points in A to µ. We first show that a multiplicative (1 + Ε) approximation to µ can be found with probability 1 − δ using O(Ε−1 log δ−1) many independent uniform random samples, and provide a matching lower bound. Furthermore, we give two sublinear time algorithms with optimal sample complexity for extracting a suitable approximate mean: 1. A gradient descent approach running in time O((Ε−1 + log log δ−1) · log δ−1 · d). It optimizes the geometric median objective while being significantly faster for our specific setting than all other known algorithms for this problem. 2. An order statistics and clustering approach running in time O ((Ε−1 + logγ δ−1) · log δ−1 · d) for any constant γ > 0. Throughout our analysis, we also generalize the familiar median-of-means estimator to the multivariate case, showing that the geometric median-of-means estimator achieves an optimal sample complexity for estimating µ, which may be of independent interest. © 2024, CC BY.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Micro-Architectural features as soft-error markers in embedded safety-critical systems: preliminary study

Micro-Architectural features as soft-error markers in embedd...

引用

IEEE European Test Symposium (ETS)

作者： Deniz Kasap Alessio Carpegna Alessandro Savino Stefano Di Carlo Bilkent University Ankara Turkey Control and Computer Engineering Department Politecnico di Torino Torino Italy

Radiation-induced soft errors are one of the most challenging issues in Safety Critical Real-Time Embedded System (SACRES) reliability, usually handled using different flavors of Double Modular Redundancy (DMR) techniques. This solution is becoming unaffordable due to the complexity of modern micro-processors in all domains. This paper addresses the promising field of using Artificial Intelligence (AI) based hardware detectors for soft errors. To create such cores and make them general enough to work with different software applications, micro-architectural attributes are a fascinating option as candidate fault detection features. Several processors already track these features through dedicated Performance Monitoring Unit (PMU). However, there is an open question to understand to what extent they are enough to detect faulty executions. Exploiting the capability of gem5 to simulate real computing systems, perform fault injection experiments, and profile micro-architectural attributes (i.e., gem5 Stats), this paper presents the results of a comprehensive analysis regarding the potential attributes to detect soft errors and the associated models that can be trained with these features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modular Model Reduction of Interconnected Systems: A Top-Down Approach

引用

IFAC-PapersOnLine 2023年第2期56卷 4246-4251页

作者： Lars A.L. Janssen Bart Besselink Rob H.B. Fey Nathan van de Wouw Dynamics and Control group Department of Mechanical Engineering Eindhoven University of Technology Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen

Complex systems often involve interconnected subsystem models developed by multi-disciplinary teams. To simulate and control such systems, a reduced-order model of the interconnected system is required. In the scope of this paper, we pursue this goal by subsystem reduction to warrant modularity of the reduction approach. However, reducing subsystem models affects not only the subsystems accuracy, but also the interconnected model accuracy, making it difficult to predict a priori the accuracy impact of subsystem reduction. To address this challenge, we introduce a top-down approach using mathematical tools from robust performance analysis, enabling the translation of accuracy requirements from the interconnected model to the subsystem level. This enables independent subsystem reduction while ensuring the desired accuracy of the interconnected model. We demonstrate the effectiveness of our approach through a structural dynamics case study.

关键词： Complex systems Model reduction control of interconnected systems Robust performance Top-down approach Error bounds

来源：评论

学校读者我要写书评

暂无评论

Binary Stochastic Flip Optimization for Training Binary Neural Networks

Binary Stochastic Flip Optimization for Training Binary Neur...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tatsukichi Shibuya Nakamasa Inoue Rei Kawakami Ikuro Sato Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in fine-tuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO

关键词： Training Speech coding Memory management Signal processing algorithms Signal processing Classification algorithms Servers Speech processing Optimization Image classification

来源：评论

学校读者我要写书评

暂无评论

WARA-PS:a research arena for public safety demonstrations and autonomous collaborative rescue robotics experimentation

引用

Autonomous Intelligent Systems 2021年第1期1卷 104-134页

作者： Olov Andersson Patrick Doherty Mårten Lager Jens-Olof Lindh Linnea Persson Elin A.Topp Jesper Tordenlid Bo Wahlberg Department of Computer and Information Science Linköping UniversityLinköpingSweden Saab Kockums MalmöSweden Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of TechnologyStockholmSweden Department of Computer Science Lund UniversityLundSweden Saab Combitech AB LinköpingSweden Division of Automatic Control Department of Electrical EngineeringLinköping UniversityLinköpingSweden

A research arena(WARA-PS)for sensing,data fusion,user interaction,planning and control of collaborative autonomous aerial and surface vehicles in public safety applications is *** objective is to demonstrate scientific discoveries and to generate new directions for future research on autonomous systems for societal *** enabler is a computational infrastructure with a core system architecture for industrial and academic *** includes a control and command system together with a framework for planning and executing tasks for unmanned surface vehicles and aerial *** motivating application for the demonstration is marine search and rescue operations.A state-of-art delegation framework for the mission planning together with three specific applications is also *** first one concerns model predictive control for cooperative rendezvous of autonomous unmanned aerial and surface *** second project is about learning to make safe real-time decisions under uncertainty for autonomous vehicles,and the third one is on robust terrain-aided navigation through sensor fusion and virtual reality tele-operation to support a GPS-free positioning system in marine *** research results have been experimentally evaluated and demonstrated to industry and public sector audiences at a marine test *** would be most difficult to do experiments on this large scale without the WARA-PS research ***,these demonstrator activities have resulted in effective research dissemination with high public visibility,business impact and new research collaborations between academia and industry.

关键词： Autonomous systems Intelligent system architectures Research demonstration arena Autonomous drones Autonomous marine vessels Public safety and security Collaborative robotics

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptive Optimal controllers for Linear Time-Delay Systems *

Learning Adaptive Optimal Controllers for Linear Time-Delay ...

引用

American control Conference (ACC)

作者： Leilei Cui Bo Pang Zhong-Ping Jiang Control and Networks Lab Department of Electrical and Computer Engineering Tandon School of Engineering New York University Brooklyn NY USA

This paper studies the learning-based optimal control for a class of infinite-dimensional linear time-delay systems. The aim is to fill the gap of adaptive dynamic programming (ADP) where adaptive optimal control of infinite-dimensional systems is not addressed. A key strategy is to combine the classical model-based linear quadratic (LQ) optimal control of time-delay systems with the state-of-art reinforcement learning (RL) technique. Both the model-based and data-driven policy iteration (PI) approaches are proposed to solve the corresponding algebraic Riccati equation (ARE) with guaranteed convergence. The proposed PI algorithm can be considered as a generalization of ADP to infinite-dimensional time-delay systems. The efficiency of the proposed algorithm is demonstrated by the practical application arising from autonomous driving in mixed traffic environments, where human drivers’ reaction delay is considered.

关键词：

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：