检索结果-内蒙古大学图书馆

A new neighborhood function for discrete manufacturing process design optimization using generalized hill climbing algorithms

引用

JOURNAL OF MECHANICAL DESIGN 2000年第2期122卷 164-171页

作者： Vaughan, DE Jacobson, SH Armstrong, DE Univ Illinois Dept Mech & Ind Engn Urbana IL 61801 USA

Discrete manufacturing process design optimization curt be difficult, due to the large number of manufacturing process design sequences and associated input parameter setting combinations that exist. Generalized hill climbing algorithms have been introduced to address such manufacturing design problems. Initial results with generalized hill climbing algorithms required the manufacturing process design sequence to be fixed with the generalized hill climbing algorithm used to identify optimal input parameter settings. This paper introduces a new neighborhood function that allows generalized hill climbing algorithms to be used to also identify the optimal discrete manufacturing process design sequence among a set of valid design sequences. The neighborhood function uses a switch function for all the input parameters, hence allows the generalized hill climbing algorithm to simultaneously optimize over both the design sequences and the inputs parameters. Computational results are reported with art integrated blade rotor discrete manufacturing process design problem under study at the Materials Process Design. Branch of the Air Force Research Laboratory, Wright Patterson Air Force Base (Dayton, Ohio, USA). [S1050-0472(00)01002-3].

关键词： manufacturing design stochastic algorithms optimization hill climbing

来源：评论

学校读者我要写书评

暂无评论

Depth-2 neural networks under a data-poisoning attack

引用

NEUROCOMPUTING 2023年 532卷 56-66页

作者： Karmakar, Sayar Mukherjee, Anirbit Papamarkou, Theodore Univ Florida Dept Stat 230 Newell Dr Gainesville FL 32611 USA Univ Manchester Dept Comp Sci Kilburn BldgOxford Rd Manchester M13 9PL England Univ Manchester Dept Math Alan Turing BldgOxford Rd Manchester M13 9PL Lancashire England

In this work, we study the possibility of defending against data-poisoning attacks while training a shallow neural network in a regression setup. We focus on doing supervised learning with realizable labels for a class of depth-2 finite-width neural networks, which includes single-filter convolutional networks. In this class of networks, we attempt to learn the true network weights generating the labels in the presence of a malicious oracle doing stochastic, bounded and additive adversarial distortions on the true labels, during training. For the gradient-free stochastic algorithm that we construct, we prove worstcase near-optimal trade-offs among the magnitude of the adversarial attack, the weight approximation accuracy, and the confidence achieved by the proposed algorithm. As our algorithm uses minibatching, we analyze how the mini-batch size affects convergence. We also show how to utilize the scaling of the outer layer weights to counter data-poisoning attacks on true labels depending on the probability of attack. Lastly, we give experimental evidence demonstrating how our algorithm outperforms stochastic gradient descent under different input data distributions, including instances of heavy-tailed distributions.(c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Convolutional neural networks stochastic algorithms Data poisoning Robust regression

来源：评论

学校读者我要写书评

暂无评论

Large deviations for a random walk model with state-dependent noise

引用

SIAM JOURNAL ON CONTROL AND OPTIMIZATION 2003年第3期42卷 810-838页

作者： Boué, M Hernández-Hernández, D Ellis, RS Trent Univ Dept Math Peterborough ON K9L 1Z6 Canada Ctr Invest Matemat Guanajuato 36000 Gto Mexico Univ Massachusetts Dept Math Amherst MA 01003 USA

In this paper we prove the large deviation principle for a class of random walks with state-dependent noise. This type of model has important applications in queueing and communication theory and in the area of stocha... 详细信息

关键词： stochastic algorithms large deviations Laplace principle weak convergence

来源：评论

学校读者我要写书评

暂无评论

Biogeography Based optimization with Salp Swarm optimizer inspired operator for solving non-linear continuous optimization problems

引用

ALEXANDRIA ENGINEERING JOURNAL 2023年 73卷 321-341页

作者： Garg, Vanita Deep, Kusum Alnowibet, Khalid Abdulaziz Zawbaa, Hossam M. Mohamed, Ali Wagdy Galgotias Univ Sch Basic & Appl Sci Greater Noida India Indian Inst Technol Dept Math Roorkee 247667 Uttarakhand India King Saud Univ Coll Sci Stat & Operat Res Dept POB 2455 Riyadh 11451 Saudi Arabia Technol Univ Dublin Dublin Ireland Cairo Univ Fac Grad Studies Stat Res Operat Res Dept Giza 12613 Egypt Appl Sci Private Univ Appl Sci Res Ctr Amman Jordan

In this paper, a novel attempt is made to incorporate the two effective algorithm strate-gies, where BBO has a strong exploration and Salp Swarm Algorithm (SSA) is used for exploitation of the search space. The proposed algorithm is tested on IEEE CEC 2014 and statistical, conver-gence graphs are given. The proposed algorithm is also applied to 10 real life problems and com-pared with its counterpart algorithm. Results obtained by above experiments have demonstrated the outperformance of the hybrid version of BBO over other algorithms. (c) 2023 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University. This is an open access article under the CC BY-NC-ND license (http://***/ licenses/by-nc-nd/4.0/).

关键词： Salp Swarm Algorithm Biogeography Based Opti-mization Exploitation Exploration stochastic algorithms

来源：评论

学校读者我要写书评

暂无评论

LARES: An artificial chemical process approach for optimization

引用

EVOLUTIONARY COMPUTATION 2004年第4期12卷 435-459页

作者： Irizarry, R DuPont Elect Microcircuits Ind Manati PR 00674 USA

This article introduces a new global optimization procedure called LARES. LARES is based on the concept of an artificial chemical process (ACP), a new paradigm which is described in this article. The algorithm's performance was studied using a test bed with a wide spectrum of problems including random multi-modal random problem generators, random LSAT problem generators with various degrees of epistasis, and a test bed of real-valued functions with different degrees of multi-modality, discontinuity and flatness. In all cases studied, LARES performed very well in terms of robustness and efficiency.

关键词： global optimization stochastic algorithms

来源：评论

学校读者我要写书评

暂无评论

Inhomogeneous functionals and approximations of invariant distributions of ergodic diffusions: Central limit theorem and moderate deviation asymptotics

引用

stochastic PROCESSES AND THEIR APPLICATIONS 2021年 133卷 74-110页

作者： Ganguly, Arnab Sundar, P. Louisiana State Univ Dept Math Baton Rouge LA 70803 USA

The paper studies asymptotics of inhomogeneous integral functionals of an ergodic diffusion process under the effect of discretization. Convergence to the corresponding functionals of the invariant distribution is shown for suitably chosen discretization steps, and the fluctuations are analyzed through central limit theorem and moderate deviation principle. The results will be particularly useful for understanding accuracy of an Euler discretization based numerical scheme for approximating functionals of invariant distribution of an ergodic diffusion. This is an infinite-time horizon problem, and the accuracy of numerical schemes in this context are comparatively much less studied than the ones used for generating approximate trajectories of diffusions over finite time intervals. The potential applications of these results also extend to other areas including mathematical physics, parameter inference of ergodic diffusions and analysis of multiscale dynamical systems with averaging. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Estimation of invariant distributions Ergodic diffusions Euler approximation Central limit theorem Large and moderate deviations stochastic algorithms

来源：评论

学校读者我要写书评

暂无评论

On map merging

引用

ROBOTICS AND AUTONOMOUS SYSTEMS 2005年第1期53卷 1-14页

作者： Carpin, S Birk, A Jucikas, V Int Univ Bremen Sch Sci & Engn D-28725 Bremen Germany

We illustrate our experience in developing and implementing algorithms for map merging, i.e., the problem of fusing two or more partial maps without common reference frames into one large global map. The partial maps may for example be acquired by multiple robots, or during several runs of a single robot from varying starting positions. Our work deals with low quality maps based on probabilistic grids, motivated by the goal to develop multiple mobile platforms to be used in rescue environments. Several contributions to map merging are presented. First of all, we address map merging using a motion planning algorithm. The merging process can be done by rotating and translating the partial maps until similar regions overlap. Second, a motion planning algorithm is presented which is particular suited for this task. Third, a special metric is presented which guides the motion planning algorithm towards the goal of optimally overlapping partial maps. Results with our approach are presented based on data gathered from real robots developed for the RoboCupRescue real robot league. (c) 2005 Elsevier B.V. All rights reserved.

关键词： stochastic algorithms rescue robotics cooperative multi-robot systems

来源：评论

学校读者我要写书评

暂无评论

Optimal placements of flexible objects .2. A simulated annealing approach for the bounded case

引用

IEEE TRANSACTIONS ON COMPUTERS 1997年第8期46卷 905-929页

作者： Albrecht, A Cheung, SK Hui, KC Leung, KS Wong, CK CHINESE UNIV HONG KONG DEPT MECH & AUTOMAT ENGN SHATIN NT HONG KONG

This paper is a continuation of the first part, where we considered regular arrangements of flexible objects for the unbounded case. The present part deals with a simulated annealing algorithm maximizing the number of flexible objects in equilibrium placements within rigid boundaries. The forces caused by the boundary are taken into account, i.e., the bounded case of placements is considered. The simulated annealing procedure makes use of the special structure of the underlying configuration space and relationships between deformations of flexible objects and resulting forces. This allows us to obtain tight bounds for the n(3/2).ln(5/2)n and ***(2)n time bounds, respectively, for the computation of equilibrium states by annealing parameters which result in n two different cooling schedules. The deformation/force formula is derived from a physical model of flexible discs and is based on numerical experiments which were performed for different materials and different sizes of objects. The algorithm was first implemented and tested for the unbounded case. The run-time is relatively short, even for large numbers of placed discs. These results are compared to the analytical ones obtained for regular placements in the first part of the paper, and agreement between these two sets of results are observed. Furthermore, several experiments for placements with boundary conditions were carried out and the resulting placements clearly show the effect of the forces from the rigid boundary. The specialized and provably efficient simulated annealing algorithm proposed in this paper is therefore a very effective tool for computing equilibrium states of placements and hence useful for the design of new amorphous polymeric materials and package cushioning systems as mentioned in Part I of this paper.

关键词： combinatorial optimization placement problems stochastic algorithms simulated annealing composite materials

来源：评论

学校读者我要写书评

暂无评论

A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental algorithms

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2017年第1期18卷 5164-5198页

作者： Zhang, Huishuai Zhou, Yi Liang, Yingbin Chi, Yuejie Syracuse Univ Dept EECS Syracuse NY 13244 USA Ohio State Univ Dept ECE Columbus OH 43210 USA

We study the problem of solving a quadratic system of equations, i.e., recovering a vector signal x is an element of R-n from its magnitude measurements y(i) = ||, i = 1,..., m. We develop a gradient descent algorithm... 详细信息

We study the problem of solving a quadratic system of equations, i.e., recovering a vector signal x is an element of R-n from its magnitude measurements y(i) = |< a(i), x(i)>|, i = 1,..., m. We develop a gradient descent algorithm (referred to as RWF for reshaped Wirtinger flow) by minimizing the quadratic loss of the magnitude measurements. Comparing with Wirtinger flow (WF) (Candes et al., 2015), the loss function of RWF is nonconvex and nonsmooth, but better resembles the least-squares loss when the phase information is also available. We show that for random Gaussian measurements, RWF enjoys linear convergence to the true signal as long as the number of measurements is O(n). This improves the sample complexity of WF (O(n log n)), and achieves the same sample complexity as truncated Wirtinger flow (TWF) (Chen and Candes, 2015), but without any sophisticated truncation in the gradient loop. Furthermore, RWF costs less computationally than WF, and runs faster numerically than both WF and TWF. We further develop an incremental (stochastic) version of RWF (IRWF) and connect it with the randomized Kaczmarz method for phase retrieval. We demonstrate that IRWF outperforms existing incremental as well as batch algorithms with experiments.

关键词： gradient descent phase retrieval nonconvex optimization regularity condition stochastic algorithms

来源：评论

学校读者我要写书评

暂无评论

An affine combination of two LMS adaptive filters - Transient mean-square analysis

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2008年第5期56卷 1853-1864页

作者： Bershad, Neil J. Bennudez, Jose Carlos M. Toumeret, Jean-Yves Univ Calif Irvine Dept Elect Engn & Comp Sci Newport Beach CA 92660 USA Univ Fed Santa Catarina Dept Elect Engn BR-88040900 Florianopolis SC Brazil ENSEEIHT TESA IRIT Toulouse 7 France

This paper studies the statistical behavior of an affine combination of the outputs of two least mean-square (LMS) adaptive filters that simultaneously adapt using the same white Gaussian inputs. The purpose of the combination is to obtain an LMS adaptive filter with fast convergence and small steady-state mean-square deviation (MSD). The linear combination studied is a generalization of the convex combination, in which the combination factor lambda(n) is restricted to the interval (0,1). The viewpoint is taken that each of the two filters produces dependent estimates of the unknown channel. Thus, there exists a sequence of optimal affine combining coefficients which minimizes the mean-square error (MSE). First, the optimal unrealizable affine combiner is studied and provides the best possible performance for this class. Then two new schemes are proposed for practical applications. The mean-square performances are analyzed and validated by Monte Carlo simulations. With proper design, the two practical schemes yield an overall MSD that is usually less than the MSDs of either filter.

关键词： adaptive filters affine combination analysis convex combination least mean square (LMS) stochastic 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：