SARASOM: a supervised architecture based on the recurrent associative SOM

Abstract We present and evaluate a novel supervised recurrent neural network architecture, the SARASOM, based on the associative self-organizing map. The performance of the SARASOM is evaluated and compared with the Elman network as well as with a hidden Markov model (HMM) in a number of prediction tasks using sequences of letters, including some experiments with a reduced lexicon of 15 words. The results were very encouraging with the SARASOM learning better and performing with better accuracy than both the Elman network and the HMM.

[1]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[2]  Rob J Hyndman,et al.  25 years of time series forecasting , 2006 .

[3]  Benjamin Schrauwen,et al.  A comparative study of Reservoir Computing strategies for monthly time series prediction , 2010, Neurocomputing.

[4]  Erkki Oja,et al.  Time series prediction competition: The CATS benchmark , 2007, Neurocomputing.

[5]  Yanchun Liang,et al.  An Improved Elman Neural Network with Profit Factors and Its Applications , 2006, ICIC.

[6]  Josphat Igadwa Mwasiagi,et al.  Self Organizing Maps - Applications and Novel Algorithm Design , 2011 .

[7]  Allam Appa Rao,et al.  A clinical decision support system using multi-layer perceptron neural network to predict quality of life in diabetes , 2010 .

[8]  Bogdan Gabrys,et al.  Meta-learning for time series forecasting in the NN GC1 competition , 2010, International Conference on Fuzzy Systems.

[9]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[10]  A.E. Diaz,et al.  Tool for the design and implementation of control systems with neural networks , 2009, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[11]  J. Elman.  Distributed Representations, Simple Recurrent Networks, And Grammatical Structure , 1991 .

[12]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[13]  Christian Balkenius,et al.  Experiments with Self-Organizing Systems for Texture and Hardness Perception , 2009 .

[14]  S. Eddy.  Hidden Markov models. , 1996, Current opinion in structural biology.

[15]  David Gil Méndez,et al.  Predicting seminal quality with artificial intelligence methods , 2012, Expert Syst. Appl..

[16]  Christian Balkenius,et al.  Associative Self-organizing Map , 2009, IJCCI.

[17]  Christian Balkenius,et al.  Ikaros: Building cognitive models for robots , 2010, Adv. Eng. Informatics.

[18]  Héctor Pomares,et al.  Soft-computing techniques and ARMA model for time series prediction , 2008, Neurocomputing.

[19]  Christian Balkenius,et al.  Internal Simulation in a Bimodal System , 2011, SCAI.

[20]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[21]  Christian Balkenius,et al.  Associating SOM Representations of Haptic Submodalities , 2008 .

[22]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[23]  David Gil Méndez,et al.  Application of artificial neural networks in the diagnosis of urological dysfunctions , 2009, Expert Syst. Appl..

[24]  Takashi Hiyama,et al.  Improving Elman Network using genetic algorithm for bearing failure diagnosis of induction motor , 2009, 2009 IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives.

[25]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[26]  Kwok-Wing Chau,et al.  Data-driven models for monthly streamflow time series prediction , 2010, Eng. Appl. Artif. Intell..

[27]  David W. Masterson,et al.  Information Extraction from Multi-Document Threads , 2003 .

[28]  Mahmut Firat,et al.  Comparative analysis of neural network techniques for predicting water consumption time series , 2010 .

[29]  Christian Balkenius,et al.  Supervised Architectures for Internal Simulation of Perceptions and Actions , 2010, BICS 2010.

[30]  John Moody,et al.  Architecture Selection Strategies for Neural Networks: Application to Corporate Bond Rating Predicti , 1995, NIPS 1995.

[31]  Fevzullah Temurtas,et al.  A comparative study on thyroid disease diagnosis using neural networks , 2009, Expert Syst. Appl..

[32]  Magnus Johnsson,et al.  Internal simulation of perceptions and actions. , 2011, Advances in experimental medicine and biology.