Encoding subcomponents in cooperative co-evolutionary recurrent neural networks

Date

2011-10-01

Author

Chandra, Rohitash
Frean, Marcus
Zhang, Mengjie
Omlin, Christian W.

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

98
views

0
downloads

Cooperative coevolution employs evolutionary algorithms to solve a high-dimensional search problem by decomposing it into low-dimensional subcomponents. Efficient problem decomposition methods or encoding schemes group interacting variables into separate subcomponents in order to solve them separately where possible. It is important to find out which encoding schemes efficiently group subcomponents and the nature of the neural network training problem in terms of the degree of non-separability. This paper introduces a novel encoding scheme in cooperative coevolution for training recurrent neural networks. The method is tested on grammatical inference problems. The results show that the proposed encoding scheme achieves better performance when compared to a previous encoding scheme.

Subject Keywords

Cooperative coevolution, Neuro-evolution, Recurrent neural networks, Grammatical inference, Genetic algorithms

URI

https://hdl.handle.net/11511/67713

Journal

NEUROCOMPUTING

DOI

https://doi.org/10.1016/j.neucom.2011.05.003

Collections

Engineering, Article

Suggestions

OpenMETU
Core

Optimization of well placement geothermal reservoirs using artificial intelligence Akın, Serhat; Kök, Mustafa Verşan (2010-06-01) This research proposes a framework for determining the optimum location of an injection well using an inference method, artificial neural networks and a search algorithm to create a search space and locate the global maxima. A complex carbonate geothermal reservoir (Kizildere Geothermal field, Turkey) production history is used to evaluate the proposed framework. Neural networks are used as a tool to replicate the behavior of commercial simulators, by capturing the response of the field given a limited numb...
Optimization of well placement in complex carbonate reservoirs using artifical intelligence Uraz, İrtek; Akın, Serhat; Department of Petroleum and Natural Gas Engineering (2004) This thesis proposes a framework for determining the optimum location of an injection well by using an inference method, Artificial Neural Networks and a search algorithm to create a search space and locate the global maxima. Theoretical foundation of the proposed framework is followed by description of the field for case study. A complex carbonate reservoir, having a recorded geothermal production history is used to evaluate the proposed framework ( Kizildere Geothermal field, Turkey). In the proposed fram...
Aggregation in swarm robotic systems: Evolution and probabilistic control Soysal, Onur; Bahçeci, Erkin; Şahin, Erol (2007-08-01) In this study we investigate two approachees for aggregation behavior in swarm robotics systems: Evolutionary methods and probabilistic control. In first part, aggregation behavior is chosen as a case, where performance and scalability of aggregation behaviors of perceptron controllers that are evolved for a simulated swarm robotic system are systematically studied with different parameter settings. Using a cluster of computers to run simulations in parallel, four experiments are conducted varying some of t...
Optimizations of Patch Antenna Arrays Using Genetic Algorithms Supported by the Multilevel Fast Multipole Algorithm Onol, Can; Ergül, Özgür Salih (2014-12-01) We present optimizations of patch antenna arrays using genetic algorithms and highly accurate full-wave solutions of the corresponding radiation problems with the multilevel fast multipole algorithm (MLFMA). Arrays of finite extent are analyzed by using MLFMA, which accounts for all mutual couplings between array elements efficiently and accurately. Using the superposition principle, the number of solutions required for the optimization of an array is reduced to the number of array elements, without resorti...
DARWIN: A Genetic Algorithm Language ARSLAN, Arslan; Üçoluk, Göktürk (2013-10-29) This article describes the DARWIN Project, which is a Genetic Algorithm programming language and its C Cross-Compiler. The primary aim of this project is to facilitate experimentation of Genetic Algorithm solution representations, operators and parameters by requiring just a minimal set of definitions and automatically generating most of the program code. The syntax of the DARWIN language and an implementational overview of the the cross-compiler will be presented. It is assumed that the reader is familiar ...

Citation Formats

R. Chandra, M. Frean, M. Zhang, and C. W. Omlin, “Encoding subcomponents in cooperative co-evolutionary recurrent neural networks,” NEUROCOMPUTING, pp. 3223–3234, 2011, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/67713.