Historical Consistent Complex Valued Recurrent Neural Network
Recurrent Neural Networks are in the scope of the machine learning community for many years. In the current paper we discuss the Historical Consistent Recurrent Neural Network and its extension to the complex valued case. We give some insights into complex valued back propagation and its application to the complex valued recurrent neural network training. Finally we present the results for the the Lorenz system modeling. In the end we discuss the advantages of the proposed algorithm and give the outlook.
Keywordscomplex valued neural networks recurrent neural networks complex valued recurrent neural networks complex dynamics analysis
Unable to display preview. Download preview PDF.
- 1.Zimmermann, H.G., Grothmann, R., Schafer, A.M., Tietz, C.: Dynamical Consistent Recurrent Neural Networks. In: Proc. of the Int. Joint Conference on Neural Networks (IJCNN), vol. 3, pp. 1537–1541 Montreal (2005)Google Scholar
- 2.Schaefer, A.M., Zimmermann, H.G.: Recurrent Neural Networks are Universal Approximators. In: Proc. of International Conference on Artificial Neural Networks (ICANN), Athens. LNCS, vol. 17(4), pp. 253–263. Springer, Heidelberg (2006)Google Scholar
- 3.Zimmermann, H.G., Minin, A., Kusherbaeva, V.: Comparison of the Complex Valued and Real Valued Neural Networks Trained with Gradient Descent and Random Search Algorithms. In: European Symposium on Artificial Neural Networks, ESANN 2011 (to appear 2011)Google Scholar
- 9.Gangal, A., Kalra, P., Chauhan, S.: Performance Evaluation of Complex Valued Neural Networks Using Various Error Functions. Enformatika 23, 27–32 (2007)Google Scholar
- 10.Lorenz, E.N.: Deterministic nonperiodic flow. Lecture Supplement 20, 130–141 (1963)Google Scholar