Abstract
This paper describes experience with NEAT (NeuroEvolution of Augmenting Topologies) method which is based on evolutionary computation and optimization of neural networks structure and synaptic weights. Non-linear function XOR approximation is tested and evaluated with this method with the aim of perspective application in humanoid robot NAO. The experiments show that selected method NEAT is suitable for this type of adaptation of NN, because of its ability to deal with the problems which emerge in TWEAN methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sinčák, P., Andrejková, G.: Neuron Networks (engineering approach) part 1 and part 2, Elfa, Kosice (1996) (in Slovak)
Mach, M.: Evolutionary Algorithms – Elements and Principles. Elfa, Kosice (2009) ISBN 978-80-8086-123-0
Kvasnička, V., Pospíchal, J., Tiňo, P.: Evolutionary Algorithms. STU, Bratislava (2000) (in Slovak) ISBN 80-227-1377-5
Mařík, V., Štěpánková, O., Lažanský, J., et al.: Artificial Intelligence 3. Academia, Praha (2001) (in Czech) ISBN 80-200-0472-6
Mařík, V., Štěpánková, O., Lažanský, J., et al.: Artificial Intelligence 4. Academia, Praha (2003) (in Czech) ISBN 80-200-1044-0
Stanley, K.O., Miikkulainen, R.: Evolving Neural Networks through Augmenting Topologies. The MIT Press Journals (2002)
Stanley, K.O., Miikkulainen, R.: Efficient Evolution of Neural Network Topogies. In: Proceedings of 2002 Congerss on Evolutionary Coputation. IEEE, Piscataway (2002)
Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Real-Time Neuroevolution in the NERO Video Game. IEEE Transactions on Evolutionary Computation (2005)
Tuhársky, J., Reiff, T., Sinčák, P.: Evolutionary Approach for Structural and Parametric Adaptation of BP-like Multilayer Neural Networks. In: Proceedings of the 10th International Symposium of Hungarian Researchers on Computational Intelligence and Informatics, Budapest, Hungary, November 12-14, pp. 41–52 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Tuhársky, J., Sinčák, P. (2010). Neural Networks Adaptation with NEAT-Like Approach. In: Rudas, I.J., Fodor, J., Kacprzyk, J. (eds) Computational Intelligence in Engineering. Studies in Computational Intelligence, vol 313. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15220-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-15220-7_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15219-1
Online ISBN: 978-3-642-15220-7
eBook Packages: EngineeringEngineering (R0)