Effects of supervised Self Organising Maps parameters on classification performance.

Self Organising Maps (SOMs) are one of the most powerful learning strategies among neural networks algorithms. SOMs have several adaptable parameters and the selection of appropriate network architectures is required in order to make accurate predictions. The major disadvantage of SOMs is probably due to the network optimisation, since this procedure can be often time-expensive. Effects of network size, training epochs and learning rate on the classification performance of SOMs are known, whereas the effect of other parameters (type of SOMs, weights initialisation, training algorithm, topology and boundary conditions) are not so obvious. This study was addressed to analyse the effect of SOMs parameters on the network classification performance, as well as on their computational times, taking into consideration a significant number of real datasets, in order to achieve a comprehensive statistical comparison. Parameters were contemporaneously evaluated by means of an approach based on the design of experiments, which enabled the investigation of their interaction effects. Results highlighted the most important parameters which influence the classification performance and enabled the identification of the optimal settings, as well as the optimal architectures to reduce the computational time of SOMs.

[1]  Lutgarde M. C. Buydens,et al.  SOMPLS: A supervised self-organising map--partial least squares algorithm for multivariate regression problems , 2007 .

[2]  I. Kuzmanovski,et al.  Optimization of supervised self-organizing maps with genetic algorithms for classification of urinary calculi , 2005 .

[3]  Max A. Little,et al.  Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection , 2007, Biomedical engineering online.

[4]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[5]  Mahdi Vasighi,et al.  A MATLAB toolbox for Self Organizing Maps and supervised neural network learning strategies , 2012 .

[6]  Sergio J. Rey,et al.  Effects of Irregular Topology in Spherical Self-Organizing Maps , 2011 .

[7]  L. Buydens,et al.  Supervised Kohonen networks for classification problems , 2006 .

[8]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[9]  Bruce Curry,et al.  Evaluating Kohonen's learning rule: An approach through genetic algorithms , 2004, Eur. J. Oper. Res..

[10]  Zou Xiaobo,et al.  Use of FT-NIR spectrometry in non-invasive measurements of soluble solid contents (SSC) of ‘Fuji’ apple based on different PLS models , 2007 .

[11]  J. Zupan,et al.  On the use of counterpropagation artificial neural networks to characterize Italian rice varieties , 2004 .

[12]  Mahdi Vasighi,et al.  Genetic Algorithms for architecture optimisation of Counter-Propagation Artificial Neural Networks , 2011 .

[13]  S. Lanteri,et al.  Chemometric analysis of Tuscan olive oils , 1989 .

[14]  Jure Zupan,et al.  Kohonen and counterpropagation artificial neural networks in analytical chemistry , 1997 .

[15]  Michael Sylvester Packianather,et al.  Optimizing the parameters of multilayered feedforward neural networks through Taguchi design of experiments , 2000 .

[16]  J. Faraway.  Linear Models with R , 2014 .

[17]  I-Cheng Yeh,et al.  Knowledge discovery on RFM model using Bernoulli sequence , 2009, Expert Syst. Appl..

[18]  Qing-You Zhang,et al.  Structure-Based Classification of Chemical Reactions without Assignment of Reaction Centers , 2005, J. Chem. Inf. Model..

[19]  Igor Kuzmanovski,et al.  Classification of perovskites with supervised self-organizing maps. , 2007, Analytica chimica acta.

[20]  Shih-Ming Yang,et al.  Neural Network Design by Using Taguchi Method , 1999 .

[21]  Etienne Barnard,et al.  Optimization for training neural nets , 1992, IEEE Trans. Neural Networks.

[22]  Fabrizio Costa,et al.  Relationships between apple texture and rheological parameters by means of multivariate analysis , 2012 .

[23]  Davide Ballabio,et al.  The Kohonen and CP-ANN toolbox: A collection of MATLAB modules for Self Organizing Maps and Counterpropagation Artificial Neural Networks , 2009 .

[24]  Federico Marini,et al.  Artificial neural networks in foodstuff analyses: Trends and perspectives A review. , 2009, Analytica chimica acta.

[25]  Tony R. Martinez,et al.  The general inefficiency of batch training for gradient descent learning , 2003, Neural Networks.

[26]  N. Bingham,et al.  Regression: Linear Models in Statistics , 2010 .

[27]  Manuela Pavan,et al.  CAIMAN (Classification and Influence Matrix Analysis) : A new approach to the classification based on leverage-scaled functions , 2007 .

[28]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[29]  O. Mangasarian,et al.  Multisurface method of pattern separation for medical diagnosis applied to breast cytology. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[30]  Marjana Novic,et al.  Automatic adjustment of the relative importance of different input variables for optimization of counter-propagation artificial neural networks. , 2009, Analytica chimica acta.

[31]  B. S. Lim,et al.  Optimal design of neural networks using the Taguchi method , 1995, Neurocomputing.

[32]  J. Ross Quinlan,et al.  Simplifying Decision Trees , 1987, Int. J. Man Mach. Stud..

[33]  Johann Gasteiger,et al.  Neural networks with counter-propagation learning strategy used for modelling , 1995 .

[34]  Michael Schmuker,et al.  SOMMER: self-organising maps for education and research , 2006, Journal of molecular modeling.

[35]  Federico Marini,et al.  Class-modeling using Kohonen artificial neural networks , 2005 .

[36]  José Manuel Amigo,et al.  A chemometric approach to the environmental problem of predicting toxicity in contaminated sediments , 2010 .

[37]  Qing-You Zhang,et al.  Random Forest Prediction of Mutagenicity from Empirical Physicochemical Descriptors , 2007, J. Chem. Inf. Model..

[38]  José Manuel Amigo,et al.  Development of models for predicting toxicity from sediment chemistry by partial least squares-discriminant analysis and counter-propagation artificial neural networks. , 2010, Environmental pollution.

[39]  Sungzoon Cho,et al.  Effects of varying parameters on properties of self-organizing feature maps , 1996, Neural Processing Letters.

[40]  H. Labelle,et al.  Analysis of the Sagittal Balance of the Spine and Pelvis Using Shape and Orientation Parameters , 2005, Journal of spinal disorders & techniques.