Abstract
The purpose of this research is to develop effective parallel Flexible Neural Tree learning algorithm based on Message Passing Interface at High Performance Computing environment. The implemented framework utilizes two bio-inspired evolutionary algorithms that were parallelized. Genetic algorithm is used to develop structure of FNT and differential evolution for fine tunning of the parameters. Framework was tested for its correctness and scalability on Anselm cluster. Scalability experiments prove good performance results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Detailed specification for Anselm can be found on the web https://docs.it4i.cz/anselm-cluster-documentation/hardware-overview.
References
Nadal, J.P.: Study of a growth algorithm for a feedforward network. Int. J. Neural Syst. 1, 55–59 (1989)
Zhang, B.T., Ohm, P., Mühlenbein, H.: Evolutionary Induction of Sparse Neural Trees. MIT Press (1997)
Chen, Y., Chen, F., Yang, J.Y.: Evolving MIMO Flexible Neural Trees for Nonlinear System Identification. CSREA Press (2007)
Chen, Y., Peng, L., Abraham, A.: Gene Expression Profiling Using Flexible Neural Trees. Springer, Berlin Heidelberg (2006)
Chen, Y., Abraham, A.: Tree-Structure based Hybrid Computational Intelligence: Theoretical Foundations and Applications. Springer (2010)
Peng, L., Yang, B., Zhang, L., Chen, Y.: A parallel evolving algorithm for flexible neural tree. Elsevier Science Publishers B. V. (2011)
Salam, A., Kader, A., Wahed, A.: Comparative study between differential evolution and particle swarm optimization algorithms in training of feed-forward neural network for stock price prediction. IEEE (2010)
Indiana University: MPI.NET: High-Performance C# Library for Message Passing (2015). http://www.osl.iu.edu/research/mpi.net/. Accessed 28 Feb 2015
Message Passing Interface Forum: MPI: a message-passing interface standard: Version 2.2 (2015). http://www.mpi-forum.org/docs/mpi-2.2/mpi22-report.pdf. Accessed 28 Feb 2015
Willcock, J., Lumsdaine, A., Robison, A.: Using MPI with C# and the common language infrastructure. ACM (2002)
Box, G., Jenkins, G.: Time Series Analysis: Forecasting and Control. Holden-Day, San Francisco (1970)
Acknowledgements
Work is supported by Grant of SGS No. SP2016/68 and SP2016/97, VŠB - Technical University of Ostrava, Czech Republic.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Hanzelka, J., Dvorský, J. (2017). Flexible Neural Trees—Parallel Learning on HPC. In: Chaki, R., Saeed, K., Cortesi, A., Chaki, N. (eds) Advanced Computing and Systems for Security. Advances in Intelligent Systems and Computing, vol 568. Springer, Singapore. https://doi.org/10.1007/978-981-10-3391-9_4
Download citation
DOI: https://doi.org/10.1007/978-981-10-3391-9_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3390-2
Online ISBN: 978-981-10-3391-9
eBook Packages: EngineeringEngineering (R0)