Filters








6,423 Hits in 5.5 sec

EMORBFN: An Evolutionary Multiobjetive Optimization Algorithm for RBFN Design [chapter]

Pedro L. López, Antonio J. Rivera, M. Dolores Pérez-Godoy, María J. del Jesus, Cristóbal Carmona
2009 Lecture Notes in Computer Science  
To test the behavior of EMORBFN a similar mono-objective optimization algorithm for Radial Basis Function Network design has been developed.  ...  In this paper a multiobjective optimization algorithm for the design of Radial Basis Function Networks is proposed.  ...  Managing only the accuracy objective to optimize RBFNs, like in traditional evolutionary computation, may lead to obtain nets with a high number of RBFs.  ... 
doi:10.1007/978-3-642-02478-8_94 fatcat:5cqs4sbqhneolirog3ci5ph5fe

Improving generalization of radial basis function network with adaptive multi-objective particle swarm optimization

Sultan Noman Qasem, Siti Mariyam Hj. Shamsuddin
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
Keywords-Radial basis function network, Adaptive Multiobjective particle swarm optimization, Multi-Objective particle swarm optimization I.  ...  These particles evolve toward Pareto-optimal front defined by several objective functions with model accuracy and complexity.  ...  RBF NETWORK AND MULTI-OBJECTIVE OPTIMIZATION A. RBF Network An ANN using radial basis function (RBF) as activation function instead of sigmoid functions is RBF network.  ... 
doi:10.1109/icsmc.2009.5346876 dblp:conf/smc/QasemS09 fatcat:utp4ros4hrchvaspz5yk7nyxee

AUTOMATED FUEL MANAGEMENT OPTIMIZATION FOR FAST REACTORS

Michael Jarrett, Florent Heidet, M. Margulis, P. Blaise
2021 EPJ Web of Conferences  
In this work, a general algorithm for optimizing a core reload of a fast reactor with respect to some objective function is developed.  ...  In the results, the evolutionary algorithm demonstrates good responsiveness to the tuning of the parameters of the objective function.  ...  The work reported in this summary is the results of R&D studies supporting a VTR concept, cost, and schedule estimate for DOE-NE to make a decision on procurement in the future.  ... 
doi:10.1051/epjconf/202124712006 fatcat:5shffgdrqvgqlgpsoteylvdddq

Multi objective optimization of computationally expensive multi-modal functions with RBF surrogates and multi-rule selection

Taimoor Akhtar, Christine A. Shoemaker
2015 Journal of Global Optimization  
A multi objective search utilizing evolution, local search, multi method search and non-dominated sorting is done on the surrogate radial basis function surface because it is inexpensive to compute.  ...  The results are compared to ParEGO (a kriging surrogate method solving many weighted single objective optimizations) and the widely used NSGA-II.  ...  Later they introduced a non-evolutionary algorithm Stochastic-RBF [37] , which is a very effective radial basis function-based method for single objective optimization of expensive global optimization  ... 
doi:10.1007/s10898-015-0270-y fatcat:55d5dymxzzgpxh5rgox4xczxya

Fuzzy-logical Control Models of Nonlinear Dynamic Objects

Siddikov Isamiddin Xakimovich, Umurzakova Dilnoza Maxamadjonovna
2020 Advances in Science, Technology and Engineering Systems  
Parameters of fuzzy controllers are optimized using a genetic algorithm. A two-step controller tuning scheme for a nonlinear dynamic object is proposed.  ...  At the second step, using a genetic algorithm, a nonlinear transforming function is formed for each channel, implemented on the basis of an artificial neural network.  ...  Acknowledgment This research received no specific grant from any funding agency in the public, commercial or not-for-profit sectors.  ... 
doi:10.25046/aj050449 fatcat:rb2g4egxfjbkdluacytvxh5kqy

The Application of Data Fusion Technology Based on Neural Network in the Dynamic Risk Assessment

Cheng Xiaorong, Ni Yang Dan, Wang Yingc
2012 Physics Procedia  
Based on diversified tools for network security management, this paper proposes to fuses a variety of information sources and then output the results of classification.  ...  Also, I shall extend my thanks to my collaborator Wang Ying for all his encouragement and support.  ...  Hidden node's net input" is defined as distance's Euclidean norm from the input sample to the center vector of radial basis function The output of hidden nodes is a radial basis function which for the  ... 
doi:10.1016/j.phpro.2012.03.297 fatcat:k6bxlrcmavfzhpmpvkjqesaoti

Surrogate-Assisted Evolutionary Optimization Frameworks for High-Fidelity Engineering Design Problems [chapter]

Yew Soon Ong, P. B. Nair, A. J. Keane, K. W. Wong
2005 Studies in Fuzziness and Soft Computing  
Over the last decade, Evolutionary Algorithms (EAs) have emerged as a powerful paradigm for global optimization of multimodal functions.  ...  Since EAs typically require thousands of function evaluations to locate a near optimal solution, the use of EAs often becomes computationally prohibitive for this class of problems.  ...  Note that any positive-definite parameterized radial basis kernel K can be employed as a covariance function.  ... 
doi:10.1007/978-3-540-44511-1_15 fatcat:akme3pq77bc7fjdkra3zzlq7iy

A comprehensive survey of fitness approximation in evolutionary computation

Y. Jin
2003 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
However, fitness evaluations are not always straightforward in many real-world applications.  ...  Evolutionary algorithms (EAs) have received increasing interests both in the academy and industry.  ...  -Radial-Basis-Function Networks The theory of radial-basis-function (RBF) networks can also be tracked back to interpolation problems [62] .  ... 
doi:10.1007/s00500-003-0328-5 fatcat:2bgqqkyslnbd3btq5qpbuc4kiy

A Classification Based Surrogate-Assisted Evolutionary Algorithm for Expensive Many-Objective Optimization

Linqiang Pan, Cheng He, Ye Tian, Handing Wang, Xingyi Zhang, Yaochu Jin
2018 IEEE Transactions on Evolutionary Computation  
Most existing surrogate-assisted evolutionary algorithms are designed for solving low-dimensional single or multiobjective optimization problems, which are not well suited for many-objective optimization  ...  Surrogate-assisted evolutionary algorithms have been developed mainly for solving expensive optimization problems where only a small number of real fitness evaluations are allowed.  ...  two-archive algorithm for many-objective optimization (Two Arch2) [18] , the reference vector based evolutionary algorithm (RVEA) [13] , and the region division based many-objective optimization evolutionary  ... 
doi:10.1109/tevc.2018.2802784 fatcat:2m565mwnazh4vg36vlh3xh6igi

Efficient Multi-Objective Optimization through Population-based Parallel Surrogate Search [article]

Taimoor Akhtar, Christine A. Shoemaker
2019 arXiv   pre-print
Multi-Objective Optimization (MOO) is very difficult for expensive functions because most current MOO methods rely on a large number of function evaluations to get an accurate solution.  ...  We develop an MOO algorithm MOPLS-N for expensive functions that combines iteratively updated surrogate approximations of the objective functions with a structure for efficiently selecting a population  ...  The support at NUS was from the Singapore National Research Foundation, Prime Minister's Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme (E2S2  ... 
arXiv:1903.02167v1 fatcat:xnvwghchq5hujlbijz3nnd66pm

Semi-supervised learning assisted particle swarm optimization of computationally expensive problems

Chaoli Sun, Yaochu Jin, Ying Tan
2018 Proceedings of the Genetic and Evolutionary Computation Conference on - GECCO '18  
., the solutions that have not been evaluated using the expensive fitness functions, generated during the optimization.  ...  In many real-world optimization problems, it is very time-consuming to evaluate the performance of candidate solutions because the evaluations involve computationally intensive numerical simulations or  ...  The reader can refer to [4] for more details. Radial Basis Function Network RBF networks are one class of commonly utilized surrogate models.  ... 
doi:10.1145/3205455.3205596 dblp:conf/gecco/SunJT18 fatcat:darmszapang2bgvvdtqaie4pu4

Surrogate-assisted multicriteria optimization: Complexities, prospective solutions, and business case

Richard Allmendinger, Michael T. M. Emmerich, Jussi Hakanen, Yaochu Jin, Enrico Rigoni
2017 Journal of Multi-Criteria Decision Analysis  
For example, complexities may relate to the appropriate selection of metamodels for the individual objective functions, extensive training time of surrogate models, or the optimal use of many-core computers  ...  The presence of multiple objective functions poses an additional layer of complexity for surrogateassisted optimization.  ...  Coello Coello for actively taking part in those discussions and Dr. Karthik Sindhya for his help related to creation of a virtual library for benchmarking.  ... 
doi:10.1002/mcda.1605 fatcat:5ew65lket5azppoo4uw546wdna

Evolutionary Optimization of Computationally Expensive Problems via Surrogate Modeling

Yew S. Ong, Prasanth B. Nair, Andrew J. Keane
2003 AIAA Journal  
In contrast to earlier work, we construct local surrogate models using radial basis functions motivated by the principle of transductive inference.  ...  We employ a trust-region approach for interleaving use of exact models for the objective and constraint functions with computationallycheap surrogate models during local search.  ...  The authors thank the anonymous referees and editors for their constructive comments on an earlier draft of this paper.  ... 
doi:10.2514/2.1999 fatcat:2kngafvllzhyljmabw2m3p3h2a

Hybrid evolutionary algorithm with Hermite radial basis function interpolants for computationally expensive adjoint solvers

Y. S. Ong, K. Y. Lum, P. B. Nair
2007 Computational optimization and applications  
We propose the idea of using Hermite interpolation to construct gradient-enhanced radial basis function networks that incorporate sensitivity data provided by the adjoint Euler solver.  ...  In this paper, we present an evolutionary algorithm hybridized with a gradient-based optimization technique in the spirit of Lamarckian learning for efficient design optimization.  ...  Concluding Remarks In this paper, we have presented a hybrid evolutionary algorithm that leverages Hermite radial basis function interpolants for optimization of computationally expensive adjoint solvers  ... 
doi:10.1007/s10589-007-9065-5 fatcat:iraktbd3mjh7hkwqeyy3ixe53y

A Federated Data-Driven Evolutionary Algorithm for Expensive Multi/Many-objective Optimization [article]

Jinjin Xu, Yaochu Jin, Wenli Du
2021 arXiv   pre-print
To this end, we leverage federated learning for surrogate construction so that multiple clients collaboratively train a radial-basis-function-network as the global surrogate.  ...  This paper aims to propose a federated data-driven evolutionary multi-/many-objective optimization algorithm.  ...  supported by National Natural Science Foundation of China (Basic Science Center Program: 61988101), International (Regional) Cooperation and Exchange Project(61720106008), National Natural Science Fund for  ... 
arXiv:2106.12086v1 fatcat:2cnpqii4rffcvkhqtttxrpg4ai
« Previous Showing results 1 — 15 out of 6,423 results