ABSTRACT
Current grammar-based NeuroEvolution approaches have several shortcomings. On the one hand, they do not allow the generation of Artificial Neural Networks (ANNs) composed of more than one hidden-layer. On the other, there is no way to evolve networks with more than one output neuron. To properly evolve ANNs with more than one hidden-layer and multiple output nodes there is the need to know the number of neurons available in previous layers. In this paper we introduce Dynamic Structured Grammatical Evolution (DSGE): a new genotypic representation that overcomes the aforementioned limitations. By enabling the creation of dynamic rules that specify the connection possibilities of each neuron, the methodology enables the evolution of multi-layered ANNs with more than one output neuron. Results in different classification problems show that DSGE evolves effective single and multi-layered ANNs, with a varying number of output neurons.
- Fardin Ahmadizar, Khabat Soltanian, Fardin AkhlaghianTab, and Ioannis Tsoulos. 2015. Artificial neural network development by means of a novel combination of grammatical evolution and genetic algorithm. Engineering Applications of Artificial Intelligence 39 (2015), 1-13.Google ScholarCross Ref
- Filipe Assuncao, Nuno Lourenco, Penousal Machado, and Bernardete Ribeiro. 2017. Automatic Generation of Neural Networks with Structured Grammatical Evolution. In 2017 IEEE Congress on Evolutionary Computation (CEC). IEEE.Google Scholar
- Omid E David and Iddo Greental. 2014. Genetic algorithms for evolving deep neural networks. In Proceedings of the 2014 Conf. companion on Genetic and evolutionary computation companion. ACM, 1451-1452. Google ScholarDigital Library
- Lucian-Ovidiu Fedorovici, Radu-Emil Precup, Florin Dragan, and Constantin Purcaru. 2013. Evolutionary optimization-based training of convolutional neural networks for OCR applications. In System Theory, Control and Computing (ICSTCC), 2013 17th International Conf. IEEE, 207-212.Google Scholar
- Limin Fu and Enzo Medico. 2007. FLAME, a novel fuzzy clustering method for the analysis of DNA microarray data. BMC bioinformatics 8, 1 (2007), 1.Google Scholar
- Faustino Gomez, Jürgen Schmidhuber, and Risto Miikkulainen. 2008. Accelerated neural evolution through cooperatively coevolved synapses. Journal of Machine Learning Research 9, May (2008), 937-965. Google ScholarDigital Library
- R. Paul Gorman and Terrence J. Sejnowski. 1988. Analysis of hidden units in a layered network trained to classify sonar targets. Neural networks 1, 1 (1988), 75-89.Google Scholar
- Frederic Gruau. 1992. Genetic synthesis of boolean neural networks with a cell rewriting developmental process. In International Workshop on Combinations of Genetic Algorithms and Neural Networks, COGANN-92. IEEE, 55-74. Google ScholarDigital Library
- Jae-Yoon Jung and James A Reggia. 2006. Evolutionary design of neural network architectures using a descriptive encoding language. IEEE transactions on evolutionary computation 10, 6 (2006), 676-688. Google ScholarDigital Library
- M. Lichman. 2013. UCI ML Repository. (2013). archive.ics.uci.edu/mlGoogle Scholar
- Nuno Lourenco, Francisco B. Pereira, and Ernesto Costa. 2016. Unveiling the properties of structured grammatical evolution. Genetic Programming and Evolvable Machines (2016), 1-39. Google ScholarDigital Library
- Miguel Rocha, Paulo Cortez, and José Neves. 2007. Evolution of neural networks for classification and regression. Neurocomputing 70, 16 (2007), 2809-2816. Google ScholarDigital Library
- Conor Ryan, JJ Collins, and Michael O'Neill. 1998. Grammatical evolution: Evolving programs for an arbitrary language. Springer Berlin Heidelberg, Berlin, Heidelberg, 83-96. Google ScholarDigital Library
- Tapas Si, Arunava De, and Anup Kumar Bhattacharjee. 2014. Grammatical Swarm for Artificial Neural Network Training. In International Conference on Circuit, Power and Computing Technologies (ICCPCT). IEEE, 1657-1661.Google Scholar
- Vincent G. Sigillito, Simon P. Wing, Larrie V. Hutton, and Kile B. Baker. 1989. Classification of radar returns from the ionosphere using neural networks. Johns Hopkins APL Technical Digest 10, 3 (1989), 262-266.Google Scholar
- Khabat Soltanian, Fardin Akhlaghian Tab, Fardin Ahmadi Zar, and Ioannis Tsoulos. 2013. Artificial neural networks generation using grammatical evolution. In 21st Iranian Conference on Electrical Engineering (ICEE). IEEE, 1-5.Google ScholarCross Ref
- Kenneth O Stanley and Risto Miikkulainen. 2002. Evolving neural networks through augmenting topologies. Evolutionary computation 10, 2 (2002), 99-127. Google ScholarDigital Library
- W. Nick Street, William H. Wolberg, and Olvi L. Mangasarian. 1993. Nuclear feature extraction for breast tumor diagnosis. In IS&T/SPIE's Symposium on Electronic Imaging: Science and Technology. International Society for Optics and Photonics, 861-870.Google Scholar
- Sreenivas Sremath Tirumala, S Ali, and C Phani Ramesh. 2016. Evolving deep neural networks: A new prospect. In Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), 2016 12th International Conf. on. IEEE, 69-74.Google Scholar
- Ioannis Tsoulos, Dimitris Gavrilis, and Euripidis Glavas. 2008. Neural network construction and training using grammatical evolution. Neurocomputing 72, 1 (2008), 269-277. Google ScholarDigital Library
- Darrell Whitley, Timothy Starkweather, and Christopher Bogart. 1990. Genetic algorithms and neural networks: Optimizing connections and connectivity. Parallel computing 14, 3 (1990), 347-361.Google Scholar
Recommendations
Evolution of Layer Based Neural Networks: Preliminary Report
GECCO '16 Companion: Proceedings of the 2016 on Genetic and Evolutionary Computation Conference CompanionModern applications of Artificial Neural Networks (ANNs)largely feature networks organized into layers of nodes. Each layer contains an arbitrary number of nodes, and these nodes only share edges with nodes in certain other layers, as determined by the ...
Towards designing artificial neural networks by evolution
Special issue on articficial life and roboticsDesigning artificial neural networks (ANNs) for different applications has been a key issue in the ANN field. At present, ANN design still relies heavily on human experts who have sufficient knowledge about ANNs and the problem to be solved. As ANN ...
Classification error of multilayer perceptron neural networks
In subject classification, artificial neural networks (ANNS) are efficient and objective classification methods. Thus, they have been successfully applied to the numerous classification fields. Sometimes, however, classifications do not match the real ...
Comments