A Particle Swarm Optimization Approach for Training Artificial Neural Networkswith Uncertain Data

Abstract. Artificial neural networks are powerful tools to learn functional relationships between data. They are widely used in engineering applications. Recurrent neural networks for fuzzy data have been introduced to map uncertain structural processes with deterministic or uncertain network parameters. Based on swarm intelligence, a new training strategy for neural networks is presented in this paper. Accounting for uncertainty in measurements, particle swarm optimization (PSO) approaches using interval and fuzzy numbers are developed. Applications are focused on the description of time-dependent material behavior with recurrent neural networks for uncertain data within interval and fuzzy finite element analyses. Network training with PSO allows to create special network structures with dependent parameters in order to consider physical boundary conditions of investigated materials.

[1]  Kamran Behdinan,et al.  Particle swarm approach for structural design optimization , 2007 .

[2]  Michael R. Lyu,et al.  A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training , 2007, Appl. Math. Comput..

[3]  Denys Breysse,et al.  Soil-structure interaction: Parameters identification using particle swarm optimization , 2010 .

[4]  Wolfgang Graf,et al.  Recurrent Neural Networks for Uncertain Time‐Dependent Structural Behavior , 2010, Comput. Aided Civ. Infrastructure Eng..

[5]  Steffen Freitag,et al.  Modeling of materials with fading memory using neural networks , 2009 .

[6]  Michael R. Lyu,et al.  A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training , 2007, Appl. Math. Comput..

[7]  Wolfgang Graf,et al.  Identification and Prediction of Time-Dependent Structural Behavior with Recurrent Neural Networks for Uncertain Data , 2010 .

[8]  Wolfgang Graf,et al.  Prediction of Time-Dependent Structural Responses with Recurrent Neural Networks , 2010 .

[9]  Ramon E. Moore.  Methods and applications of interval analysis , 1979, SIAM studies in applied mathematics.

[10]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[11]  David Moens,et al.  A survey of non-probabilistic uncertainty treatment in finite element analysis , 2005 .

[12]  Robert L. Mullen,et al.  A new interval finite element formulation with the same accuracy in primary and derived variables , 2011 .

[13]  Hao Zhang,et al.  Interval Finite Elements as a Basis for Generalized Models of Uncertainty in Engineering Mechanics , 2007, Reliab. Comput..

[14]  Sobri Harun,et al.  Particle swarm optimization feedforward neural network for modeling runoff , 2010 .

[15]  Wolfgang Graf,et al.  Prediction of uncertain structural behaviour and robust design , 2011 .

[16]  Wolfgang Graf,et al.  Prediction of time-dependent structural behaviour with recurrent neural networks for fuzzy data , 2011 .

[17]  M. Beer,et al.  Engineering computation under uncertainty - Capabilities of non-traditional models , 2008 .

[18]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[19]  Hojjat Adeli,et al.  Neural Networks in Civil Engineering: 1989–2000 , 2001 .

[20]  Q. H. Wu,et al.  A heuristic particle swarm optimizer for optimization of pin connected structures , 2007 .

[21]  Paulo Cortez,et al.  Particle swarms for feedforward neural network training , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[22]  Wolfgang Graf,et al.  Recurrent neural networks for fuzzy data , 2011, Integr. Comput. Aided Eng..

[23]  Yuhui Shi,et al.  Particle swarm optimization: developments, applications and resources , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[24]  Mauro Birattari,et al.  Swarm Intelligence , 2012, Lecture Notes in Computer Science.

[25]  W. Graf,et al.  Fuzzy structural analysis using α-level optimization , 2000 .