ABSTRACT
In this paper, we propose a scheme for evolving multiple-input-multiple-output (MIMO) artificial neural networks (ANNs) using grammatical evolution (GE). GE is a well-known technique for program evolution. While it has also been used for the evolution of ANN structures in the past, little work is reported on the evolution of MIMO ANNs.
MIMO ANNs are important for problems that have multiple outputs. Examples are controllers for autonomous systems such as unmanned aerial vehicles (UAVs) and driver-less cars that take in multiple inputs and are expected to produce multiple outputs simultaneously such as speed, steering etc. Certain regression problems are also MIMO in nature. Our results are promising.
- Mohamed Abou-Zleikha and Noor Shaker. 2015. Evolving random forest for preference learning. In European Conference on the Applications of Evolutionary Computation. Springer, 318--330.Google ScholarCross Ref
- 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
- etal Assuncao. 2017. Automatic generation of neural networks with structured Grammatical Evolution. 2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings Section IV (2017), 1557--1564.Google Scholar
- Filipe Assunçao, Nuno Lourenço, Penousal Machado, and Bernardete Ribeiro. 2017. Automatic generation of neural networks with structured grammatical evolution. In Evolutionary Computation (CEC), 2017 IEEE Congress on. IEEE, 1557--1564.Google ScholarDigital Library
- Filipe Assunçao, Nuno Lourenço, Penousal Machado, and Bernardete Ribeiro. 2017. Towards the evolution of multi-layered neural networks: a dynamic structured grammatical evolution approach. In Proceedings of the Genetic and Evolutionary Computation Conference. ACM, 393--400. Google ScholarDigital Library
- Filipe Assunçao, Nuno Lourenço, Penousal Machado, and Bernardete Ribeiro. 2018. DENSER: Deep Evolutionary Network Structured Representation. arXiv preprint arXiv:1801.01563 (2018).Google Scholar
- Filipe Assunção, Nuno Lourenço, Penousal Machado, and Bernardete Ribeiro. 2018. Evolving the Topology of Large Scale Deep Neural Networks. In European Conference on Genetic Programming. Springer, 19--34.Google Scholar
- Federico Castejón and Enrique J Carmona. 2018. Automatic design of analog electronic circuits using grammatical evolution. Applied Soft Computing 62 (2018), 1003--1018.Google ScholarCross Ref
- JM Colmenar, JI Hidalgo, and S Salcedo-Sanz. 2018. Automatic generation of models for energy demand estimation using Grammatical Evolution. Energy (2018).Google ScholarCross Ref
- Iván Contreras, J Ignacio Hidalgo, and Laura Nunez-Letamendia. 2017. A hybrid automated trading system based on multi-objective grammatical evolution. Journal of Intelligent & Fuzzy Systems 32, 3 (2017), 2461--2475.Google ScholarCross Ref
- Iván Contreras, Silvia Oviedo, Martina Vettoretti, Roberto Visentin, and Josep Vehí. 2017. Personalized blood glucose prediction: A hybrid approach using grammatical evolution and physiological models. PloS one 12, 11 (2017), e0187754.Google ScholarCross Ref
- Dua Dheeru and Efi Karra Taniskidou. 2017. UCI Machine Learning Repository. http://archive.ics.uci.edu/mlGoogle Scholar
- Pasi Fränti and Sami Sieranoja. 2018. K-means properties on six clustering benchmark datasets. http://cs.uef.fi/sipu/datasets/Google Scholar
- Limin Fu and Enzo Medico. 2007. FLAME, a novel fuzzy clustering method for the analysis of DNA microarray data. BMC Bioinformatics 8 (2007).Google Scholar
- Edgar Galván-López, John Mark Swafford, Michael OâĂŹNeill, and Anthony Brabazon. 2010. Evolving a ms. pacman controller using grammatical evolution. In European Conference on the Applications of Evolutionary Computation. Springer, 161--170. Google ScholarDigital Library
- J Ignacio Hidalgo, J Manuel Colmenar, José L Risco-Martin, Alfredo Cuesta-Infante, Esther Maqueda, Marta Botella, and José Antonio Rubio. 2014. Modeling glycemia in humans by means of grammatical evolution. Applied Soft Computing 20 (2014), 40--53.Google ScholarCross Ref
- Jonatan Hugosson, Erik Hemberg, Anthony Brabazon, and Michael OâĂŹNeill. 2010. Genotype representations in grammatical evolution. Applied Soft Computing 10, 1 (2010), 36--43. Google ScholarDigital Library
- DE Kazaryan and AV Savinkov. 2017. Grammatical evolution for neural network optimization in the control system synthesis problem. Procedia Computer Science 103 (2017), 14--19. Google ScholarDigital Library
- Nuno Lourenço, Francisco B Pereira, and Ernesto Costa. 2016. Unveiling the properties of structured grammatical evolution. Genetic Programming and Evolvable Machines 17, 3 (2016), 251--289. Google ScholarDigital Library
- Olvi L Mangasarian, W Nick Street, and William H Wolberg. 1995. Breast cancer diagnosis and prognosis via linear programming. Operations Research 43, 4 (1995), 570--577. Google ScholarDigital Library
- Eric Medvet, Alberto Bartoli, Andrea De Lorenzo, and Fabiano Tarlao. 2018. Designing automatically a representation for grammatical evolution. Genetic Programming and Evolvable Machines (12 Jul 2018). Google ScholarDigital Library
- Eric Medvet, Alberto Bartoli, and Jacopo Talamini. 2017. Road Traffic Rules Synthesis Using Grammatical Evolution. In European Conference on the Applications of Evolutionary Computation. Springer, 173--188.Google Scholar
- Thambo Nyathi and Nelishia Pillay. 2018. Comparison of a genetic algorithm to grammatical evolution for automated design of genetic programming classification algorithms. Expert Systems with Applications 104 (2018), 213--234.Google ScholarCross Ref
- Michael O'Neill, Erik Hemberg, Conor Gilligan, Eliott Bartley, James McDermott, and Anthony Brabazon. 2008. GEVA: grammatical evolution in Java. ACM SIGEVOlution 3, 2 (2008), 17--22. Google ScholarDigital Library
- M. O'Neill and C. Ryan. 2001. Grammatical evolution. IEEE Transactions on Evolutionary Computation 5, 4 (Aug 2001), 349--358. Google ScholarDigital Library
- Diego Perez, Miguel Nicolau, Michael OâĂŹNeill, and Anthony Brabazon. 2011. Evolving behaviour trees for the mario ai competition using grammatical evolution. In European Conference on the Applications of Evolutionary Computation. Springer, 123--132. Google ScholarDigital Library
- Michael Phelan and Seán McGarraghy. 2016. Grammatical evolution in developing optimal inventory policies for serial and distribution supply chains. International Journal of Production Research 54, 1 (2016), 336--364.Google ScholarCross Ref
- Terrence J Sejnowski. 1988. Analysis of Hidden Units in a Layered Network. 1 (1988), 75--89.Google Scholar
- etal Sigillito. 1989. Classification of radar returns from the ionosphere using neural networks. Johns Hopkins APL Technical Digest (Applied Physics Laboratory) 10, 3 (1989), 262--266.Google Scholar
- Alexander Topchy and William F Punch. 2001. Faster genetic programming based on local gradient search of numeric leaf values. In Proceedings of the 3rd Annual Conference on Genetic and Evolutionary Computation. Morgan Kaufmann Publishers Inc., 155--162. Google ScholarDigital Library
- Ioannis Tsoulos, Dimitris Gavrilis, and Euripidis Glavas. 2008. Neural network construction and training using grammatical evolution. Neurocomputing 72, 1--3 (2008), 269--277. Google ScholarDigital Library
- Jose Manuel Velasco, Oscar Garnica, Juan Lanchares, Marta Botella, and J Ignacio Hidalgo. 2018. Combining data augmentation, EDAs and grammatical evolution for blood glucose forecasting. Memetic Computing (2018), 1--11.Google Scholar
- Jan Žegklitz and Petr Pošík. 2015. Symbolic Regression by Grammar-based Multi-Gene Genetic Programming. In Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation (GECCO Companion '15). ACM, New York, NY, USA, 1217--1220. Google ScholarDigital Library
Recommendations
Neural network construction and training using grammatical evolution
The term neural network evolution usually refers to network topology evolution leaving the network's parameters to be trained using conventional algorithms. In this paper we present a new method for neural network evolution that evolves the network ...
A new grammatical evolution method for generating deep convolutional neural networks with novel topologies
GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference CompanionNeuroevolution, a sub-field of AutoML, utilizes evolutionary algorithms to automate the process of creating Deep Neural Networks architectures. For problems with complex objects, such as neural networks, Grammar-based Evolutionary Algorithms (GEs) can be ...
Comments