Abstract
Two-hidden-layer feedforward neural networks are investigated for the existence of an optimal hidden node ratio. In the experiments, the heuristic \( n_{1} = int(0.5n_{h} + 1 \)), where \( n_{1} \) is the number of nodes in the first hidden layer and \( n_{h} \) is the total number of hidden nodes, found networks with generalisation errors, on average, just 0.023 %–0.056 % greater than those found by exhaustive search. This reduced the complexity of an exhaustive search from quadratic, to linear in \( n_{h} \), with very little penalty. Further reductions in search complexity to logarithmic could be possible using existing methods developed by the Authors.
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
Similar content being viewed by others
References
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Mocanu, F.: On-board fuel identification using artificial neural networks. Int. J. Engines 7, 937–946 (2014)
Yap, W.K., Ho, T., Karri, V.: Exhaust emissions control and engine parameters optimization using artificial neural network virtual sensors for a hydrogen-powered vehicle. Int. J. Hydrog. Ener. 37, 8704–8715 (2012)
Roy, S., Banerjee, R., Das, A.K., Bose, P.K.: Development of an ANN based system identification tool to estimate the performance-emission characteristics of a CRDI assisted CNG dual fuel diesel engine. J. Nat. Gas Sci. Eng. 21, 147–158 (2014)
Taghavifar, H., Taghavifar, H., Mardani, A., Mohebbi, A.: Modeling the impact of in-cylinder combustion parameters of DI engines on soot and NOx emissions at rated EGR levels using ANN approach. Ener. Convers. Manag. 87, 1–9 (2014)
Chester, D.L.: Why two hidden layers are better than one. In: International Joint Conference on Neural Networks, vol. 1, pp. 265–268. Laurence Erlbaum, New Jersey (1990)
Huang, G.-B., Babri, H.A.: Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions. IEEE Trans. Neural Netw. 9, 224–229 (1989)
Huang, G.-B.: Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans. Neural Netw. 14, 274–281 (2003)
Kwok, T.-Y., Yeung, D.-Y.: Constructive algorithms for structure learning in feedforward neural networks for regression problems. IEEE Trans. Neural Netw. 8, 630–645 (1997)
Azzini, A., Tettamanzi, A.G.B.: Evolutionary ANNs: a state of the art survey. Intell. Artif. 5, 19–35 (2011)
Reed, R.: Pruning algorithms – a survey. IEEE Trans. Neural Netw. 4, 740–747 (1993)
Thomas, A.J., Petridis, M., Walters, S.D., Malekshahi Gheytassi, S., Morgan, R.E.: On predicting the optimal number of hidden nodes. In: 2015 International Conference on Computational Science and Computational Intelligence, pp. 565–570. IEEE CPS (2015)
UCI Machine Learning Repository. http://archive.ics.uci.edu/ml
Acknowledgements
We thank Prof. Martin T. Hagan of Oklahoma State University for kindly donating the Engine Data Set used in this paper to Matlab. We would also like to thank Dr. Roberto Lopez of Intelnics (robertolopez@intelnics.com) for donating the Airfoil Self-Noise dataset; also the dataset’s creators: Thomas F. Brooks, D. Stuart Pope and Michael A. Marcolini of NASA.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Thomas, A.J., Walters, S.D., Petridis, M., Malekshahi Gheytassi, S., Morgan, R.E. (2016). Accelerated Optimal Topology Search for Two-Hidden-Layer Feedforward Neural Networks. In: Jayne, C., Iliadis, L. (eds) Engineering Applications of Neural Networks. EANN 2016. Communications in Computer and Information Science, vol 629. Springer, Cham. https://doi.org/10.1007/978-3-319-44188-7_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-44188-7_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44187-0
Online ISBN: 978-3-319-44188-7
eBook Packages: Computer ScienceComputer Science (R0)