检索结果-内蒙古大学图书馆

computational constraints on the associative recall of spatial scenes

HIPPOCAMPUS 2023年第5期33卷 635-645页

作者： Ryom, Kwang Il Stendardi, Debora Ciaramelli, Elisa Treves, Alessandro SISSA Cognit Neurosci Trieste Italy Univ Bologna Dipartimento Psicol Renzo Canestrari Bologna Italy SISSA Cognit Neurosci Via Bonomea 265 I-34136 Trieste Italy

We consider a model of associative storage and retrieval of compositional memories in an extended cortical network. Our model network is comprised of Potts units, which represent patches of cortex, interacting through long-range connections. The critical assumption is that a memory, for example of a spatial view, is composed of a limited number of items, each of which has a pre-established representation: storing a new memory only involves acquiring the connections, if novel, among the participating items. The model is shown to have a much lower storage capacity than when it stores simple unitary representations. It is also shown that an input from the hippocampus facilitates associative retrieval. When it is absent, it is advantageous to cue rare rather than frequent items. The implications of these results for emerging trends in empirical research are discussed.

关键词： associative recall computational constraints compositional memory Potts network spatial scenes

来源：评论

学校读者我要写书评

暂无评论

Scheduling and Control Co-Design for Control Systems under computational constraints

Scheduling and Control Co-Design for Control Systems under C...

引用

20th World Congress of the International-Federation-of-Automatic-Control (IFAC)

作者： Zhao, Yun-Bo Dong, Hui Ni, Hongjie Zhejiang Univ Technol Coll Informat Engn Hangzhou 310023 Zhejiang Peoples R China

A prediction-based approach is proposed for control systems with limited and time varying computational resources. The limited and time-varying computational resources can make the control system run in an open-loop fashion which may severely degrade the system performance or even destabilize the system. This issue is dealt with by producing more than one forward control predictions when abundant computational resources are available, and then using these forward control predictions to close the system when the computational resources are insufficient to calculate real-time control signal. This achievement is made without additional requirement for the computational resources and can be regarded as a useful completion of the scheduling algorithms. With a controller designed using a modified model predictive control method, the effectiveness of the proposed approach is successfully illustrated by a numerical example. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Embedded control systems computational constraints Scheduling Co-design

来源：评论

学校读者我要写书评

暂无评论

Scheduling and Control Co-Design for Control Systems under computational constraints

引用

IFAC-PapersOnLine 2017年第1期50卷 5881-5886页

作者： Zhao Y.-B. Dong H. Ni H. College of Information Engineering Zhejiang University of Technology Hangzhou 310023 China

A prediction-based approach is proposed for control systems with limited and time-varying computational resources. The limited and time-varying computational resources can make the control system run in an open-loop fashion which may severely degrade the system performance or even destabilize the system. This issue is dealt with by producing more than one forward control predictions when abundant computational resources are available, and then using these forward control predictions to close the system when the computational resources are insufficient to calculate real-time control signal. This achievement is made without additional requirement for the computational resources and can be regarded as a useful completion of the scheduling algorithms. With a controller designed using a modified model predictive control method, the effectiveness of the proposed approach is successfully illustrated by a numerical example. © 2017

关键词： Co-design computational constraints Embedded control systems Scheduling

来源：评论

学校读者我要写书评

暂无评论

Significance Tests of Feature Relevance for a Black-Box Learner

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第2期35卷 1898-1911页

作者： Dai, Ben Shen, Xiaotong Pan, Wei Chinese Univ Hong Kong Dept Stat Hong Kong Peoples R China Univ Minnesota Sch Stat Minneapolis MN 55455 USA Univ Minnesota Div Biostat Minneapolis MN 55455 USA

An exciting recent development is the uptake of deep neural networks in many scientific fields, where the main objective is outcome prediction with a black-box nature. Significance testing is promising to address the black-box issue and explore novel scientific insights and interpretations of the decision-making process based on a deep learning model. However, testing for a neural network poses a challenge because of its black-box nature and unknown limiting distributions of parameter estimates while existing methods require strong assumptions or excessive computation. In this article, we derive one-split and two-split tests relaxing the assumptions and computational complexity of existing black-box tests and extending to examine the significance of a collection of features of interest in a dataset of possibly a complex type, such as an image. The one-split test estimates and evaluates a black-box model based on estimation and inference subsets through sample splitting and data perturbation. The two-split test further splits the inference subset into two but requires no perturbation. Also, we develop their combined versions by aggregating the p-values based on repeated sample splitting. By deflating the bias-sd-ratio, we establish asymptotic null distributions of the test statistics and the consistency in terms of Type II error. Numerically, we demonstrate the utility of the proposed tests on seven simulated examples and six real datasets. Accompanying this article is our python library dnn-inference (https://***/en/latest/) that implements the proposed tests.

关键词： Adaptive splitting black-box tests combining computational constraints feature relevance

来源：评论

学校读者我要写书评

暂无评论

Worst-case regret analysis of computationally budgeted online kernel selection

引用

MACHINE LEARNING 2022年第3期111卷 937-976页

作者： Li, Junfan Liao, Shizhong Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China

We study the problem of online kernel selection under computational constraints, where the memory or time of kernel selection and online prediction procedures is restricted to a fixed budget. In this paper, we analyze the worst-case lower bounds on the regret of online kernel selection algorithm with a subset of the observed examples, and design algorithms enjoying corresponding upper bounds. We also identify the condition under which online kernel selection with time constraints is different from that with memory constraints. To design algorithms, we reduce the problems to two sequential decision problems, that is, the problem of prediction with expert advice and the multi-armed bandit problem with an additional observation. Our algorithms invent some new techniques, such as memory sharing, hypothesis space discretization and decoupled exploration-exploitation scheme. Numerical experiments on online regression and classification are conducted to verify our theoretical results.

关键词： Online learning Kernel selection computational constraints Regret analysis

来源：评论

学校读者我要写书评

暂无评论

Complexity and mission computability of adaptive computing systems

引用

JOURNAL OF DEFENSE MODELING AND SIMULATION-APPLICATIONS METHODOLOGY TECHNOLOGY-JDMS 2022年第1期19卷 5-11页

作者： Dasari, Venkat R. Im, Mee Seong Geerhart, Billy CCDC US Army Res Lab Aberdeen Proving Ground MD 21005 USA US Mil Acad West Point NY 10996 USA

There is a subset of computational problems that existing algorithms may not complete due to a lack of adequate computational resources on tactical edge computing platforms. Although this subset is computable in polynomial time, many polynomial problems are not computable in mission time. Here, we define a subclass of deterministic polynomial time complexity called mission class, wherein the computations must complete in mission time. By focusing on this subclass of languages in the context of successful military applications, we discuss their computational and network constraints. We investigate feasible (non)linear models that will minimize energy and maximize memory, efficiency, and computational power, and also provide an approximate solution obtained within a pre-determined length of computation time using limited resources so that an optimal solution to a language could be determined.

关键词： Computability P versus NP problems strategic solvability mission readiness optimization computational constraints heterogeneous computational platform

来源：评论

学校读者我要写书评

暂无评论

Improving tail accuracy of the predicted cumulative distribution function of time of failure

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2021年 207卷

作者： Sierra, Gina Robinson, Elinirina, I Goebel, Kai NASA Ames Res Ctr KBR Inc SGT Moffett Field CA 94035 USA Palo Alto Res Ctr Palo Alto CA 94304 USA Lulea Univ Technol Div Operat & Maintenance Engn Lulea Sweden

Prognostic information is used to make decisions such as when to perform maintenance or - in time sensitive and safety critical applications - when to change operational settings. Where distributions about expected end of life (EOL) are available, these decisions are often based on risk-informed thresholds, for example a 2 sigma or 3 sigma criterion which considers the probability of making a bad decision at 5% or 0.3%, respectively, as tolerable. Sampling-based techniques such as Monte Carlo Sampling (MCS) and Latin Hypercube Sampling (LHS) can provide effective approaches to the propagation and analysis of uncertainty. Due to its efficient manner of stratifying across the range of each sampled variable, LHS requires less computational effort than MCS and is therefore more often used. However, since the focus is placed on accurately predicting the tails of the Cumulative Distribution Function (CDF) of Time of Failure (ToF) sampling-base techniques may not properly represent these areas. Although one might be tempted to use a brute force approach and simply increase the number of samples, some safety-critical applications may be computationally constrained. Such applications include electric UAV where the decision making process has to be fast in order to take action as soon as possible. This paper explores the ability of MCS and LHS to perform tail prediction with small sample sizes. The results show that LHS does not provide a significant advantage over MCS in terms of characterizing the tails of the CDF of the battery End of Discharge (EOD) prediction. Then, a methodology that combines MCS and Kernel Density Estimation (KDE) is investigated. The advantages of KDE in terms of reducing sample size while improving tail accuracy are demonstrated on battery end-of-discharge data.

关键词： Predicted end-of-Life distribution Risk-based decisions computational constraints Monte Carlo sampling Latin hypercube sampling Kernel density estimation Time sensitive and safety critical applications

来源：评论

学校读者我要写书评

暂无评论

Distributed State Estimation of Moving Targets Using Cyclic Simultaneous Perturbation Stochastic Approximation

引用

IFAC-PapersOnLine 2018年第23期51卷 218-223页

作者： Erofeeva, Victoria Granichin, Oleg Institute of Problems in Mechanical Engineering Russian Academy of Sciences Saint Petersburg Russia

Sensor networks comprised of multiple nodes with sensing, processing and communication capabilities are ubiquitous in tracking systems. However, when a tracking system is required to track a large number of targets, the computation and communication loads arise. One possible solution is to use a distributed scheme. In this paper we propose a distributed multiple target tracking algorithm, which takes into account restrictions on the sensor network functioning. Our method is based on the modification of Simultaneous Perturbation Stochastic Approximation (SPSA) algorithm with a perturbation on the input. For the proposed algorithm we get an upper bound of residual between estimates and show the simulation results. © 2018

关键词： Distributed computer systems Approximation algorithms Approximation theory Clutter (information theory) Optimization Sensor networks Sensor nodes State estimation Stochastic systems Target tracking Communication constraints computational constraints Distributed estimation Distributed multiple target tracking Distributed state estimation Simultaneous perturbation stochastic approximation Simultaneous perturbation stochastic approximation algorithms Stochastic approximations

来源：评论

学校读者我要写书评

暂无评论

Optimisation-based motion planning with obstacles and priorities

引用

IFAC-PapersOnLine 2017年第1期50卷 11670-11676页

作者： Greiff, Marcus Robertsson, Anders Lund University Department of Automatic Control Lund Sweden

The goal of this work is to explore ways of generating state trajectories for dynamical systems subject to computational constraints, obstacles and priority assignment. The algorithms are developed for a miniature unmanned aerial vehicle (UAV) in a modular fashion and include (1) a genetic algorithm (GA) for solving the travelling salesman problem (TSP) with respect to priorities and obstacle avoidance, (2) a projective algorithm (PA) for finding the shortest paths around obstacles, (3) a quadratic program (QP) for minimum-snap polynomial trajectory generation subject to equality constraints to guarantee avoidance of static obstacles. Combined, the algorithms enable simple and computationally efficient motion planning with support in both R2and R3exemplified in a real-time implementation. © 2017

关键词： Motion planning Antennas Dynamical systems Genetic algorithms Polynomials Quadratic programming Real time control Traveling salesman problem Unmanned aerial vehicles (UAV) computational constraints computationally efficient heuristic TSP Optimisations Polynomial trajectory projective path Real time implementations Travelling salesman problem (TSP)

来源：评论

学校读者我要写书评

暂无评论

Can bootstrapping explain concept learning?

引用

COGNITION 2017年 158卷 110-121页

作者： Beck, Jacob York Univ Dept Philosophy Toronto ON Canada York Univ Ctr Vis Res Toronto ON Canada

Susan Carey's account of Quinean bootstrapping has been heavily criticized. While it purports to explain how important new concepts are learned, many commentators complain that it is unclear just what bootstrapping is supposed to be or how it is supposed to work. Others allege that bootstrapping falls prey to the circularity challenge: it cannot explain how new concepts are learned without presupposing that learners already have those very concepts. Drawing on discussions of concept learning from the philosophical literature, this article develops a detailed interpretation of bootstrapping that can answer the circularity challenge. The key to this interpretation is the recognition of computational constraints, both internal and external to the mind, which can endow empty symbols with new conceptual roles and thus new contents. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Bootstrapping Concept learning Susan Carey Concepts computational constraints

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：