Filters








90 Hits in 4.5 sec

Competitive two-island cooperative coevolution for training Elman recurrent networks for time series prediction

Rohitash Chandra
2014 2014 International Joint Conference on Neural Networks (IJCNN)  
Neural level and Synapse level problem decomposition is used in each of the islands.  ...  It is important to add collaboration and competition in cooperative coevolution.  ...  (BPTT-RNN) (2010) TABLE VII A VII COMPARISON WITH THE RESULTS FROM LITERATURE ON THE SUNSPOT TIME SERIES Prediction Method RMSE NMSE Multi-layer perceptron (1996)  ... 
doi:10.1109/ijcnn.2014.6889421 dblp:conf/ijcnn/Chandra14 fatcat:u4xm5nlngzbrfoz7ha7mkly4mq

Multi-objective cooperative coevolution of neural networks for time series prediction

Shelvin Chand, Rohitash Chandra
2014 2014 International Joint Conference on Neural Networks (IJCNN)  
Cooperative coevolution is an evolutionary computation method that decomposes the problem into subcomponents and has shown promising results for training neural networks.  ...  The trained multi-objective neural network can give prediction of the original time series for preprocessed data sets distinguished by their time lags.  ...  The authors of [18] explored multi-objective cooperative coevolution using a special niching mechanism and an extending operator to maintain diversity.  ... 
doi:10.1109/ijcnn.2014.6889442 dblp:conf/ijcnn/ChandC14 fatcat:zkhhonpnm5d3vo35a4e2f5zray

Multi-objective cooperative coevolution of artificial neural networks (multi-objective cooperative networks)

N Garcı́a-Pedrajas, C Hervás-Martı́nez, J Muñoz-Pérez
2002 Neural Networks  
There are many applications of cooperative coevolution that could benefit from the multi-objective optimization approach proposed in this paper. q  ...  In this paper we present a cooperative coevolutive model for the evolution of neural network topology and weights, called MOBNET.  ...  Moya-Sánchez for her helping in the final version of this paper. This work has been supported in part by the Project ALI98-0676-CO2-02 of the Spanish Comisión Interministerial de Ciencia y Tecnología.  ... 
doi:10.1016/s0893-6080(02)00095-3 pmid:12425442 fatcat:z2pzopequvee7jcndu4eltfyv4

Evolution of Cooperation in Evolutionary Robotics: the Tradeoff between Evolvability and Efficiency

Arthur Bernard, Jean-Baptiste André, Nicolas Bredeche
2015 07/20/2015-07/24/2015  
In this paper, we investigate the benefits and drawbacks of different approaches for solving a cooperative foraging task with two robots.  ...  We compare a classical clonal approach with an additional approach which favors the evolution of heterogeneous behaviors according to two defining criteria: the evolvability of the cooperative solution  ...  Agents can move freely in the environment and are controlled by a fully connected multi-layer perceptron with a single hidden layer, the topology of which does not change during the evolution.  ... 
doi:10.7551/978-0-262-33027-5-ch087 dblp:conf/ecal/BernardAB15 fatcat:4snbcior2bczzpiakzcjgzwxde

Neuroevolution in Games: State of the Art and Open Challenges

Sebastian Risi, Julian Togelius
2017 IEEE Transactions on Computational Intelligence and AI in Games  
how the fitness is determined and what type of input the network receives.  ...  We analyse the application of NE in games along five different axes, which are the role NE is chosen to play in a game, the different types of neural networks used, the way these networks are evolved,  ...  ACKNOWLEDGEMENTS We thank the numerous colleagues who have graciously read and commented on versions of this paper, including Kenneth O. Stanley, Julian Miller, Matt Taylor, Mark J.  ... 
doi:10.1109/tciaig.2015.2494596 fatcat:uenp54gg2vffdolr5awox2ayx4

Neuroevolution in Games: State of the Art and Open Challenges [article]

Sebastian Risi, Julian Togelius
2015 arXiv   pre-print
how the fitness is determined and what type of input the network receives.  ...  We analyse the application of NE in games along five different axes, which are the role NE is chosen to play in a game, the different types of neural networks used, the way these networks are evolved,  ...  For example, Lucas [50] compared the performance of single and multi-layer perceptrons in a simplified version of the Ms.  ... 
arXiv:1410.7326v3 fatcat:yqynswodpnbgzdf52mlisix3hu

Genetic Algorithms and Neural Networks: A Comparison Based on the Repeated Prisoners Dilemma [chapter]

Robert E. Marks, Hermann Schnabl
1999 Advances in Computational Economics  
It turns out that the MLP (Multi-Layer Perceptron), a standard feedforward type of NN, is best suited to use in the economic context, because its ability to take into account complex situations is much  ...  The problem inherent in the criticised models was that a Multi-Layer-Perceptron (MLP), which could handle non-linear problems, lacked an efficient learning algorithm and thus was not applicable in practice  ... 
doi:10.1007/978-1-4615-5029-7_8 fatcat:beqxdpykvvduxhvvgxsh26ifpq

Engineering Evolutionary Intelligent Systems: Methodologies, Architectures and Reviews [chapter]

Ajith Abraham, Crina Grosan
2008 Studies in Computational Intelligence  
In this Chapter, we illustrate the various possibilities for designing intelligent systems using evolutionary algorithms and also present some of the generic evolutionary design architectures that has  ...  evolved during the last couple of decades.  ...  [60] used EA to optimize Hybrid Self-Organizing Fuzzy Polynomial Neural Networks (HSOFPNN)m, which are based on genetically optimized multi-layer perceptrons.  ... 
doi:10.1007/978-3-540-75396-4_1 fatcat:xplkbxzk4vbpbmnp4zxrjomj3q

2020 Index IEEE Transactions on Emerging Topics in Computational Intelligence Vol. 4

2020 IEEE Transactions on Emerging Topics in Computational Intelligence  
Cooperative Coevolution Design of Multilevel Fuzzy Logic Controllers for Media Access Control in Wireless Body Area Networks.  ...  Chen, Y., +, TETCI June 2020 369-384 Cooperative Coevolution Design of Multilevel Fuzzy Logic Controllers for Media Access Control in Wireless Body Area Networks.  ... 
doi:10.1109/tetci.2020.3042423 fatcat:qj6bpqfey5gpjhqe7zvgg644l4

On Design Mining: Coevolution and Surrogate Models

Richard J. Preen, Larry Bull
2017 Artificial Life  
Using an abstract, tuneable model of coevolution we consider strategies to sample sub-thread designs for whole system testing and how best to construct and use surrogate models within the coevolutionary  ...  Drawing on our findings, the paper then describes the effective design of an array of six heterogeneous vertical-axis wind turbines.  ...  The data used to generate the graphs is available at http://researchdata.uwe.ac.uk/166.  ... 
doi:10.1162/artl_a_00225 pmid:28513204 fatcat:sghtuwbn7zhntpfwxjgipcjfr4

Adversarial genetic programming for cyber security: a rising application domain where GP matters

Una-May O'Reilly, Jamal Toutouh, Marcos Pertierra, Daniel Prado Sanchez, Dennis Garcia, Anthony Erb Luogo, Jonathan Kelly, Erik Hemberg
2020 Genetic Programming and Evolvable Machines  
We delineate Adversarial Genetic Programming for Cyber Security, a research topic that, by means of genetic programming (GP), replicates and studies the behavior of cyber adversaries and the dynamics of  ...  We present a framework called RIVALS which supports the study of network security arms races.  ...  Either expressed or implied of Applied Communication Services, or the US Government.  ... 
doi:10.1007/s10710-020-09389-y fatcat:pptcxqfc6zeptdstzl3ipewrym

Adversarial Genetic Programming for Cyber Security: A Rising Application Domain Where GP Matters

Una-May O'Reilly, Jamal Toutouh, Marcos Pertierra, Daniel Prado Sanchez, Anthony Erb Luogo, Jonathan Kelly, Erik Hemberg
2020 Zenodo  
We delineate Adversarial Genetic Programming for Cyber Security, a research topic that, by means of genetic programming (GP), replicates and studies the behavior of cyber adversaries and the dynamics of  ...  We present a framework called RIVALS which supports the study of network security arms races.  ...  Either expressed or implied of Applied Communication Services, or the US Government.  ... 
doi:10.5281/zenodo.4593284 fatcat:mpwyc4xbhbhahlaagf44a22abe

A review of modularization techniques in artificial neural networks

Mohammed Amer, Tomás Maul
2019 Artificial Intelligence Review  
As learning problems grow in scale and complexity, and expand into multi-disciplinary territory, a more modular approach for scaling ANNs will be needed.  ...  In this review, we aim to establish a solid taxonomy that captures the essential properties and relationships of the different variants of MNNs.  ...  Acknowledgements This is a pre-print of an article published in Artificial Intelligence Review. The final authenticated version is available online at: https://doi.org/10.1007/s10462-019-09706-7  ... 
doi:10.1007/s10462-019-09706-7 fatcat:g4xp6dktvncu5dao53dcvoexoa

Dynamic Difficulty Adjustment (DDA) in Computer Games: A Review

Mohammad Zohaib
2018 Advances in Human-Computer Interaction  
The features such as frequency, starting levels, or rates can be set only at the beginning of the game by choosing a level of difficulty.  ...  This paper provides a review of the current approaches to DDA.  ...  Probabilistic Methods Pedersen, Togelius, and Yannakakis Single and multi-layered perceptrons Spronck et al.  ... 
doi:10.1155/2018/5681652 fatcat:2yopa4sq3vcqzppgrnwkat2ikm

Classification using redundant mapping in modular neural networks

Y K Meena, K V Arya, R Kala
2010 2010 Second World Congress on Nature and Biologically Inspired Computing (NaBIC)  
The limitations of the single neural network approaches motivate the use of multiple neural networks for solving the problem in the form of ensembles and modular neural networks.  ...  Classification is a major problem of study that involves formulation of decision boundaries based on the training data samples.  ...  Multi-Layer Perceptron with Back Propagation Algorithm was used for the individual networks.  ... 
doi:10.1109/nabic.2010.5716375 dblp:conf/nabic/MeenaAK10 fatcat:hxcq37cvoffqxlmdklhtvk6hne
« Previous Showing results 1 — 15 out of 90 results