The problem of complexity is here addressed by defining an upper bound for the number of the hidden layer's neurons. This majorant is evaluated by applying a singular value decomposition to the contaminated oblique subspace projection of the row space of future outputs into the past inputs'outputs row space, along the future inputs row space. Full rank projections are dealt with by i) computing the number of dominant singular values, on the basis of a threshold related to the Euclidean norm of an artificial error matrix and ii) finding the argument of minimizing the singular value criterion. Results on a benchmark three-tank system demonstrate the effectiveness of the proposed methodology.
Keywords
Neural Networks, Estimating the Number of Hidden Neurons, Three-Tank System
Subject
Neural Networks
Conference
IEEE-ISIE 2009 - IEEE International Symposium on Industrial Electronics, July 2009
Cited by
Year 2015 : 1 citations
De Mulder, Wim, Steven Bethard, and Marie-Francine Moens. "A survey on the application of recurrent neural networks to statistical language modeling." Computer Speech & Language 30, no. 1 (2015): 61-98.
Year 2014 : 3 citations
Jelil, Radhia Abd, Xianyi Zeng, Ludovic Koehl, and Anne Perwuelz. "Optimization of Plasma Fabric Surface Treatment by Modeling with Neural Networks." In Foundations and Applications of Intelligent Systems, pp. 243-256. Springer Berlin Heidelberg, 2014.
Chen, Yi?Chung, and Chiang Lee. "Neural skyline filter for accelerating skyline search algorithms." Expert Systems (2014).
Ghanmi, H., A. Ghith, and T. Benameur. "Application of artificial neural network in textile: Prediction of ring spun yarn properties." IOSR Journal of Engineering 4 (2014): 28-34.
Year 2013 : 1 citations
Abd Jelil, Radhia, Xianyi Zeng, Ludovic Koehl, and Anne Perwuelz. "Modeling plasma surface modification of textile fabrics using artificial neural networks." Engineering Applications of Artificial Intelligence 26, no. 8 (2013): 1854-1864.
Year 2012 : 1 citations
Santos, Fábio Miguel Veloso dos. "Detecção de falhas baseada em modelos identificados com recurso a técnicas de subespaços." (2012).
Year 2011 : 1 citations
Ajit Kumar Sahoo, “A Data Clustering Algorithm for Stratified Data Partitioning in Artificial Neural Network”, MSc Thesis, Department of Mechanical Engineering, University of Alberta, 2011.
