Abstract: The lecture describes a feed forward Artificial Neural Network (ANN) synthesis via an Analytic Programming (AP) by means of the ANN creation, learning and optimization. This process encompasses four different fields: Evolutionary Algorithms, Symbolic Regression, ANN and parallel computing to successfully synthetize a suitable ANN within a reasonable time. AP performes well in many separate cases together with different evolutionary algorithms as its “engine”. Direct asynchronous parallelization of SOMA – Self-Organizing Migration Algorithm is applied here to boost AP with unusual efficiency. The ANN synthesis method is applied to the real life problem of Heat Load Prediction function optimization of the heating plant in Komorany (Czech Republic) as well as on cancer classification problem and is compared with other methods. ANN synthesis proved to be a useful and efficient tool for nonlinear modeling and its results were applied to intelligent system controlling an energetic framework of an urban agglomeration.

Brief Biography of the Speaker:
Pavel Varacha graduated from Tomas Bata University in Zlin, Czech Republic in 2006. In the same year he has started to work as a lecturer on Faculty of Applied Informatics, Tomas Bata University in Zlin. Pavel Varacha develops innovative methods in the fields of evolutionary computing, parallel computation and artificial neural network optimization.. Since 2006 he frequently publishes articles and software solutions covering his scientific contributions. Between 2006 and 2011 he worked as a researcher on National Research Program II, The intelligent system controlling an energetic framework of an urban agglomeration (successfully finished in 2011). In 2008 he has started to work also in College of Logistics, Prerov, Czech Republic. From 2009 he regularly publishes within WSEAS conferences and journals. Pavel Varacha has acquired Ph.D. title in Information Technology from Tomas Bata University in Zlin (2011). He continues his scientific and pedagogic work on Department of Informatics and Artificial Intelligence, Faculty of Applied Informatics, Tomas Bata University in Zlin. Presently he is a member of WSEAS research project developing unique method of neural network optimization and learning called Neural Network Synthesis.