检索结果-内蒙古大学图书馆

Optimizing neural networks for river flow forecasting - evolutionary computation methods versus the Levenberg-Marquardt approach

引用

JOURNAL OF HYDROLOGY 2011年第1-4期407卷 12-27页

作者： Piotrowski, Adam P. Napiorkowski, Jaroslaw J. Polish Acad Sci Inst Geophys PL-01452 Warsaw Poland

Although neural networks have been widely applied to various hydrological problems, including river flow forecasting, for at least 15 years, they have usually been trained by means of gradient-based algorithms. Recently nature inspired evolutionary computation algorithms have rapidly developed as optimization methods able to cope not only with non-differentiable functions but also with a great number of local minima. Some of proposed evolutionary computation algorithms have been tested for neural networks training, but publications which compare their performance with gradient-based training methods are rare and present contradictory conclusions. The main goal of the present study is to verify the applicability of a number of recently developed evolutionary computation optimization methods, mostly from the Differential Evolution family, to multi-layer perceptron neural networks training for daily rainfall-runoff forecasting. In the present paper eight evolutionary computation methods, namely the first version of Differential Evolution (DE), Distributed DE with Explorative-Exploitative Population Families, Self-Adaptive DE, DE with Global and Local Neighbors, Grouping DE, JADE, Comprehensive Learning Particle Swarm Optimization and Efficient Population Utilization Strategy Particle Swarm Optimization are tested against the Levenberg-Marquardt algorithm - probably the most efficient in terms of speed and success rate among gradient-based methods. The Annapolis River catchment was selected as the area of this study due to its specific climatic conditions, characterized by significant seasonal changes in runoff, rapid floods, dry summers, severe winters with snowfall, snow melting, frequent freeze and thaw, and presence of river ice - conditions which make flow forecasting more troublesome. The overall performance of the Levenberg-Marquardt algorithm and the DE with Global and Local Neighbors method for neural networks training turns out to be superior to other Evolutio

关键词： Rainfall-runoff modeling Neural networks evolutionary computation Levenberg-Marquardt algorithm Differential Evolution Particle Swarm Optimization

来源：评论

学校读者我要写书评

暂无评论

Application of evolutionary computation techniques for the identification of innovators in open innovation communities

引用

EXPERT SYSTEMS WITH APPLICATIONS 2013年第7期40卷 2503-2510页

作者： Martinez-Torres, M. R. Univ Seville Fac Turismo & Finanzas Seville 41018 Spain

Open innovation represents an emergent paradigm by which organizations make use of internal and external resources to drive their innovation processes. The growth of information and communication technologies has facilitated a direct contact with customers and users, which can be organized as open innovation communities through Internet. The main drawback of this scheme is the huge amount of information generated by users, which can negatively affect the correct identification of potentially applicable ideas. This paper proposes the use of evolutionary computation techniques for the identification of innovators, that is, those users with the ability of generating attractive and applicable ideas for the organization. For this purpose, several characteristics related to the participation activity of users though open innovation communities have been collected and combined in the form of discriminant functions to maximize their correct classification. The right classification of innovators can be used to improve the ideas evaluation process carried out by the organization innovation team. Besides, obtained results can also be used to test lead user theory and to measure to what extent lead users are aligned with the organization strategic innovation policies. (c) 2012 Elsevier Ltd. All rights reserved.

关键词： Open innovation Innovation communities evolutionary computation Social network analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-objective evolutionary computation and fuzzy optimization

引用

INTERNATIONAL JOURNAL OF APPROXIMATE REASONING 2006年第1期43卷 59-75页

作者： Jimenez, F. Cadenas, J. M. Sanchez, G. Gomez-Skarmeta, A. F. Verdegay, J. L. Univ Murcia Dept Ingn Informac & Comunicac Fac Informat E-30100 Murcia Spain Univ Granada Dept Ciencias Computac & Inteligencia Artificial ETSII E-18071 Granada Spain

In fuzzy optimization it is desirable that all fuzzy solutions under consideration be attainable, so that the decision maker will be able to make "a posteriori" decisions according to current decision environments. No additional optimization runs will be needed when the decision environment changes or when the decision maker needs to evaluate several decisions to establish the most appropriate ones. In this sense, multi-objective optimization is similar to fuzzy optimization, since it is also desirable to capture the Pareto front composing the solution. The Pareto front in a multi-objective problem can be interpreted as the fuzzy solution for a fuzzy problem. Multi-objective evolutionary algorithms have been shown in the last few years to be powerful techniques in solving multi-objective optimization problems because they can search for multiple Pareto solutions in a single run of the algorithm. In this contribution, we first introduce a multi-objective approach for nonlinear constrained optimization problems with fuzzy costs and constraints, and then an "ad hoc" multi-objective evolutionary algorithm to solve the former problem. A case study of a fuzzy optimization problem arising in some import export companies in the south of Spain is analyzed and the proposed solutions from the evolutionary algorithm considered here are given. (c) 2006 Elsevier Inc. All rights reserved.

关键词： fuzzy optimization multi-objective optimization evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Reward tampering and evolutionary computation: a study of concrete AI-safety problems using evolutionary algorithms

引用

GENETIC PROGRAMMING AND EVOLVABLE MACHINES 2023年第2期24卷 1-25页

作者： Nilsen, Mathias K. Nygaard, Tonnes F. Ellefsen, Kai Olav Univ Oslo Inst Informat Harald Harfagresgate 12A N-0316 Oslo Norway

Reward tampering is a problem that will impact the trustworthiness of the powerful AI systems of the future. Reward Tampering describes the problem where AI agents bypass their intended objective, enabling unintended and potentially harmful behaviours. This paper investigates whether the creative potential of evolutionary algorithms could help ensure trustworthy solutions when facing this problem. The reason why evolutionary algorithms may help combat reward tampering is that they are able to find a diverse collection of different solutions to a problem within a single run, aiding the search for desirable solutions. Four different evolutionary algorithms were deployed in tasks illustrating the problem of reward tampering. The algorithms were designed with varying degrees of human expertise, measuring how human guidance influences the ability to discover trustworthy solutions. The results indicate that the algorithms' ability to find and preserve trustworthy solutions is very dependent on preserving diversity during the search. Algorithms searching for behavioural diversity showed to be the most effective against reward tampering. Human expertise also showed to improve the certainty and quality of safe solutions, but even with only a minimal degree of human expertise, domain-independent diversity management was found to discover safe solutions.

关键词： AI trustworthiness Reward tampering evolutionary computation Neuroevolution Behavioural diversity Quality diversity

来源：评论

学校读者我要写书评

暂无评论

Unraveling ancient mysteries: Reimagining the past using evolutionary computation in a complex gaming environment

引用

IEEE TRANSACTIONS ON evolutionary computation 2005年第6期9卷 707-720页

作者： Reynolds, RG Kobti, Z Kohler, TA Yap, LYL Wayne State Univ Dept Comp Sci Detroit MI 48202 USA Univ Michigan Dept Anthropol Ann Arbor MI 48109 USA Univ Windsor Sch Comp Sci Windsor ON N9B 3P4 Canada Washington State Univ Dept Anthropol Pullman WA 99164 USA Santa Fe Inst Santa Fe NM 87501 USA

In this paper, we use principles from game theory, computer gaming, and evolutionary computation to produce a framework for investigating one of the great mysteries of the ancient Americas: why did the pre-Hispanic Pueblo (Anasazi) peoples leave large portions of their territories in the late A.D. 1200s? The gaming concept is overlaid on a large-scale agent-based simulation of the Anasazi. Agents in this game use a cultural algorithm framework to modify their finite-state automata (FSA) controllers following the work of Fogel (1966). In the game, there can be two kinds of active agents: scripted and unscripted. Unscripted agents attempt to maximize their survivability, whereas scripted agents can be used to test the impact that various pure and compound strategies for cooperation and defection have on the social structures produced by the overall system. The goal of our experiments here is to determine the extent to which cooperation and competition need to be present among the agent households in order to produce a population structure and spatial distribution similar to what has been observed archaeologically. We do this by embedding a "trust in networks" game within the simulation. In this game, agents can choose from three pure strategies: defect, trust, and inspect. This game does not have a pure Nash equilibrium but instead has a mixed strategy Nash equilibrium such that a certain proportion of the population uses each at every time step, where the proportion relates to the quality of the signal used by the inspectors to predict defection. We use the cultural algorithm to help us determine what the mix of strategies might have been like in the prehistoric population. The simulation results indeed suggest a mixed strategy consisting of defectors, inspectors, and trustors was necessary to produce results compatible with the archaeological data. It is suggested that the presence of defectors derives from the unreliability of the signal which increases under droug

关键词： archaeological simulation complex systems computer gaming cultural algorithms defection evolution of cooperation evolutionary computation intelligent agents reciprocity

来源：评论

学校读者我要写书评

暂无评论

A Constrained evolutionary computation Method for Detecting Controlling Regions of Cortical Networks

引用

IEEE-ACM TRANSACTIONS ON computationAL BIOLOGY AND BIOINFORMATICS 2012年第6期9卷 1569-1581页

作者： Tang, Yang Wang, Zidong Gao, Huijun Swift, Stephen Kurths, Juergen Harbin Inst Technol Res Inst Intelligent Control & Syst Harbin 150080 Heilongjiang Pr Peoples R China Humboldt Univ Inst Phys D-12489 Berlin Germany Potsdam Inst Climate Impact Res Dept Transdisciplinary Concepts & Methods D-14415 Potsdam Germany Brunel Univ Dept Informat Syst & Comp Uxbridge UB8 3PH Middx England Potsdam Inst Climate Impact Res Dept Transdisciplinary Concepts & Methods D-14473 Potsdam Germany Univ Aberdeen Inst Complex Syst & Math Biol Aberdeen AB24 3UE Scotland

Controlling regions in cortical networks, which serve as key nodes to control the dynamics of networks to a desired state, can be detected by minimizing the eigenratio R and the maximum imaginary part sigma of an extended connection matrix. Until now, optimal selection of the set of controlling regions is still an open problem and this paper represents the first attempt to include two measures of controllability into one unified framework. The detection problem of controlling regions in cortical networks is converted into a constrained optimization problem (COP), where the objective function R is minimized and sigma is regarded as a constraint. Then, the detection of controlling regions of a weighted and directed complex network (e. g., a cortical network of a cat), is thoroughly investigated. The controlling regions of cortical networks are successfully detected by means of an improved dynamic hybrid framework (IDyHF). Our experiments verify that the proposed IDyHF outperforms two recently developed evolutionary computation methods in constrained optimization field and some traditional methods in control theory as well as graph theory. Based on the IDyHF, the controlling regions are detected in a microscopic and macroscopic way. Our results unveil the dependence of controlling regions on the number of driver nodes l and the constraint r. The controlling regions are largely selected from the regions with a large in-degree and a small out-degree. When r = + infinity, there exists a concave shape of the mean degrees of the driver nodes, i.e., the regions with a large degree are of great importance to the control of the networks when l is small and the regions with a small degree are helpful to control the networks when l increases. When r 0, the mean degrees of the driver nodes increase as a function of l. We find that controlling sigma is becoming more important in controlling a cortical network with increasing l. The methods and results of detecting controlling regi

关键词： Cortical networks synchronization controllability evolutionary computation constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-robot mission planning using evolutionary computation with incremental task addition

引用

INTELLIGENT SERVICE ROBOTICS 2021年第5期14卷 741-771页

作者： Kala, Rahul Indian Inst Informat Technol Ctr Intelligent Robot Allahabad Uttar Pradesh India

Mission planning asks the robot to solve complex missions, requiring the robot to execute several actions such that a complex goal condition (called mission) is satisfied. The missions can be specified by using Linear Temporal Logic or any custom domain-specific language. Here, we consider service robots in the home or office environments with multiple users, each specifying a task that together makes a mission. Conventional mission planning techniques assume that the complete mission specification is known in advance, while mission planning is incremental wherein tasks keep getting added and deleted. The exponential computational complexity of the current model verification-based approaches is not a viable solution. The paper presents an evolutionary framework for incrementally solving the problem of mission planning for the problems for which a polynomial-time verification system exists for the tasks. The optimal solution is represented in an encoding-specific format that is compiled to form a linear trajectory of the robots. Optimization is done as the robot operates. Thus, the robot at any time has a partial solution to every task that has already been executed that (along with the robot assigned to the task) cannot be altered, while a part representing the next steps of the robot to be optimized. This acts as a constraint in the continuous optimization. The proposed approach uses Dynamic Programming to integrate the solutions of tasks and as a distance function in the diversity preserving evolutionary computation since the mission constantly changes. Comparisons are made with a baseline evolutionary computation without Dynamic Programming, a non-incremental version of the proposed algorithm, and several greedy strategies. The proposed algorithm is seen to perform better than all other methods. Further, the algorithm is implemented and demonstrated on a Pioneer LX robot.

关键词： Mission planning Robot motion planning Linear temporal logic evolutionary computation Diversity preservation

来源：评论

学校读者我要写书评

暂无评论

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the evolutionary computation and Artificial Life Research Communities

引用

ARTIFICIAL LIFE 2020年第2期26卷 274-306页

作者： Lehman, Joel Clune, Jeff Misevic, Dusan Adami, Christoph Altenberg, Lee Beaulieu, Julie Bentley, Peter J. Bernard, Samuel Beslon, Guillaume Bryson, David M. Cheney, Nick Chrabaszcz, Patryk Cully, Antoine Doncieux, Stephane Dyer, Fred C. Ellefsen, Kai Olav Feldt, Robert Fischer, Stephan Forrest, Stephanie Frenoy, Antoine Gagn, Christian Le Goff, Leni Grabowski, Laura M. Hodjat, Babak Hutter, Frank Keller, Laurent Knibbe, Carole Krcah, Peter Lenski, Richard E. Lipson, Hod MacCurdy, Robert Maestre, Carlos Miikkulainen, Risto Mitri, Sara Moriarty, David E. Mouret, Jean-Baptiste Anh Nguyen Ofria, Charles Parizeau, Marc Parsons, David Pennock, Robert T. Punch, William F. Ray, Thomas S. Schoenauer, Marc Shulte, Eric Sims, Karl Stanley, Kenneth O. Taddei, Francois Tarapore, Danesh Thibault, Simon Watson, Richard Weimer, Westley Yosinski, Jason Uber AI Labs San Francisco CA 94103 USA OpenAI San Francisco CA USA Univ Paris INSERM U1284 Ctr Res & Interdisciplinar Paris France Michigan State Univ E Lansing MI 48824 USA Univ Hawaii Manoa Honolulu HI 96822 USA Univ Laval Quebec City PQ Canada UCL London England CNRS INRIA Inst Camille Jordan Paris France Univ Lyon CNRS INRIA Lyon France Univ Vermont Burlington VT 05405 USA Univ Freiburg Freiburg Germany Imperial Coll London London England UPMC Univ Paris 06 Sorbonne Univ CNRS Inst Intelligent Syst & Robot ISIR Paris France Univ Oslo Oslo Norway Chalmers Univ Technol Gothenburg Sweden INRA Paris France Arizona State Univ Tempe AZ 85287 USA Univ Grenoble Alpes Grenoble France SUNY Coll Potsdam Potsdam NY 13676 USA Cognizant Technol Solut Teaneck NJ USA Univ Lausanne Dept Fundamental Microbiol Lausanne Switzerland Charles Univ Prague Prague Czech Republic Columbia Univ New York NY 10027 USA Univ Colorado Boulder CO 80309 USA Univ Texas Austin Austin TX 78712 USA Apple Inc Cupertino CA 95014 USA INRIA Nancy Grand Fst Villers Les Nancy France Auburn Univ Auburn AL 36849 USA Univ Oklahoma Norman OK 73019 USA Univ Paris Saclay INRIA St Aubin France GrammaTech Ithaca NY USA Univ Cent Florida Orlando FL 32816 USA Univ Southampton Southampton Hants England Univ Virginia Charlottesville VA 22903 USA

Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world: Artificial organisms evolving in computational environments have also elicited surprise and wonder from the researchers studying them. The process of evolution is an algorithmic process that transcends the substrate in which it occurs. Indeed, many researchers in the field of digital evolution can provide examples of how their evolving algorithms and organisms have creatively subverted their expectations or intentions, exposed unrecognized bugs in their code, produced unexpectedly adaptations, or engaged in behaviors and outcomes, uncannily convergent with ones found in nature. Such stories routinely reveal surprise and creativity by evolution in these digital worlds, but they rarely fit into the standard scientific narrative. Instead they are often treated as mere obstacles to be overcome, rather than results that warrant study in their own right. Bugs are fixed, experiments are refocused, and one-off surprises are collapsed into a single data point. The stories themselves are traded among researchers through oral tradition, but that mode of information transmission is inefficient and prone to error and outright loss. Moreover, the fact that these stories tend to be shared only among practitioners means that many natural scientists do not realize how interesting and lifelike digital organisms are and how natural their evolution can be. To our knowledge, no collection of such anecdotes has been published before. This article is the crowd-sourced product of researchers in the fields of artificial life and evolutionary computation who have provided first-hand accounts of such cases. It thus serves as a written, fact-checked collection of scientifically important and even entertaining stories. In doing so we also present here substantial evidence that the existence and impor

关键词： Surprise creativity digital evolution experimental evolution genetic algorithms evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

New composite evolutionary computation algorithm using interactions among genetic evolution, individual learning and social learning

引用

INTELLIGENT DATA ANALYSIS 2010年第4期14卷 497-514页

作者： Hashimoto, Takashi Warashina, Katsuhide Yamauchi, Hajime JAIST Sch Knowledge Sci Nomi Ishikawa 9231292 Japan

This paper studies the characteristics of a new composite evolutionary computation algorithm in which genetic evolution, individual learning and social learning interact in NK fitness landscape. We derive conditions for effective social learning in static and dynamic environments using computer simulations of a model of the composite evolutionary algorithm. The conditions for static environments are: the individual learning cost should be at least 1.5 times than the social one;the mutation rate should be less than 0.04 per each gene;more than 3 genes should not interact. These conditions qualitatively mean that: the individual learning cost is larger than the social learning cost;teaching is beneficial for teachers;mutation rate is not too high, must be smaller than error thresold;the fitness landscape is not so complex. We also show that this algorithm is effective in dynamic environments in which NK fitness landscape changes with time, if these conditions are satisfied. Frequent environmental change favors social learning, but under more severe conditions, such as high epistasis and higher mutation rate than the error threshold, individual learning is more useful in finding better solutions.

关键词： evolutionary computation Genetic evolution Individual learning Social learning NK fitness landscape Dynamic environment

来源：评论

学校读者我要写书评

暂无评论

Applying evolutionary computation methods for the cryptanalysis of Feistel ciphers

引用

APPLIED MATHEMATICS AND computation 2007年第1期184卷 63-72页

作者： Laskari, E. C. Meletiou, G. C. Stamatiou, Y. C. Vrahatis, M. N. Univ Patras Dept Math Computat Intelligence Lab GR-26110 Patras Greece ATEI Epirus GR-47100 Arta Greece Univ Ioannina Dept Math GR-45110 Ioannina Greece Univ Patras UPAIRC GR-26110 Patras Greece

In this contribution instances of a problem introduced by the differential cryptanalysis of Feistel cryptosystems are formulated as optimization tasks. The performance of evolutionary computation methods on these tasks is studied for a representative Feistel cryptosystem, the Data Encryption Standard. The results indicate that the proposed methodology is efficient in handling this type of problems and furthermore, that its effectiveness depends mainly on the construction of the objective function. This approach is applicable to all Feistel cryptosystems that are amenable to differential cryptanalysis. (c) 2006 Elsevier Inc. All rights reserved.

关键词： computational intelligence evolutionary computation DES differential cryptanalysis Feistel ciphers

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：