FPGA Implementation of Wavelet Neural Network Training with PSO/iPSO

In this study, field-programmable gate array (FPGA)-based hardware implementation of the wavelet neural network (WNN) training using particle swarm optimization (PSO) and improved particle swarm optimization (iPSO) algorithms are presented. The WNN architecture and wavelet activation function approach that is proper for the hardware implementation are suggested in the study. Using the suggested architecture and training algorithms, test operations are implemented on two different dynamic system recognition problems. From the test results obtained, it is observed that WNN architecture generalizes well and the activation function suggested has approximately the same success rate with the wavelet function defined in the literature. In the FPGA-based implementation, IEEE 754 floating-point number format is used. Experimental tests are done on Xilinx Artix 7 xc7a100t-1csg324 using ISE Webpack 14.7 program.

[1]  Haitham Kareem Ali,et al.  Hardware Implementation of Artificial Neural Network Using Field Programmable Gate Array , 2013 .

[2]  George J. Milne,et al.  Towards an FPGA based reconfigurable computing environment for neural network implementations , 1999 .

[3]  Ju Hahn Lee,et al.  Development of FPGA-based digital signal processing system for radiation spectroscopy , 2013 .

[4]  Michel Auguin,et al.  FPGA-based generic neural network architecture , 2006, 2006 International Symposium on Industrial Embedded Systems.

[5]  Mohamed Akil,et al.  Implementation of an LVQ neural network with a variable size: algorithmic specification, architectural exploration and optimized implementation on FPGA devices , 2009, Neural Computing and Applications.

[6]  Jiwen Dong,et al.  A local linear wavelet neural network , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[7]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[8]  Amin Farmahini Farahani,et al.  Scalable Architecture for on-Chip Neural Network Training using Swarm Intelligence , 2008, 2008 Design, Automation and Test in Europe.

[9]  Nadia Nedjah,et al.  Dynamic MAC-based architecture of artificial neural networks suitable for hardware implementation on FPGAs , 2009, Neurocomputing.

[10]  Okyay Kaynak,et al.  Identification and Control of Dynamic Plants Using Fuzzy Wavelet Neural Networks , 2008, 2008 IEEE International Symposium on Intelligent Control.

[11]  David L. Elliott,et al.  A Better Activation Function for Artificial Neural Networks , 1993 .

[12]  Julio Pérez Acle,et al.  NeuroFPGA-implementing artificial neural networks on programmable logic devices , 2004, Proceedings Design, Automation and Test in Europe Conference and Exhibition.

[13]  Anton Kummert,et al.  FPGA implementation of a neural network for a real-time hand tracking system , 2002, Proceedings First IEEE International Workshop on Electronic Design, Test and Applications '2002.

[14]  E. Won,et al.  A hardware implementation of artificial neural networks using field programmable gate arrays , 2007, physics/0703041.

[15]  S. S. Shriramwar,et al.  FPGA-based Controller for a Mobile Robot , 2009, ArXiv.

[16]  Stephen A. Billings,et al.  International Journal of Control , 2004 .

[17]  Shawki Areibi,et al.  The Impact of Arithmetic Representation on Implementing MLP-BP on FPGAs: A Study , 2007, IEEE Transactions on Neural Networks.

[18]  Yasar Becerikli,et al.  Neural Network Implementation in Hardware Using FPGAs , 2006, ICONIP.

[19]  Cihan Karakuzu,et al.  Parçacık Sürü Optimizasyonu Algoritması ile Yapay Sinir Ağı Eğitiminin FPGA Üzerinde Donanımsal Gerçeklenmesi , 2010 .

[20]  Armando Astarloa,et al.  Hardware architecture for a general regression neural network coprocessor , 2007, Neurocomputing.

[21]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[22]  Cihan Karakuzu,et al.  Neural identification of dynamic systems on FPGA with improved PSO learning , 2012, Appl. Soft Comput..

[23]  Fernando Morgado Dias,et al.  A high bit resolution FPGA implementation of a FNN with a new algorithm for the activation function , 2007, Neurocomputing.

[24]  Mehmet Ali Çavuslu,et al.  Neural network training based on FPGA with floating point number format and it’s performance , 2011, Neural Computing and Applications.

[25]  Feng Lin,et al.  A Hopfield Neural Classifier and Its FPGA Implementation for Identification of Symmetrically Structured DNA Motifs , 2007, J. VLSI Signal Process..

[26]  M. Balasubramani,et al.  FPGA Implementation of Wavelet Neural Network for Epilepsy Detection , 2013 .

[27]  Adnan Kavak,et al.  Digital signal processor against field programmable gate array implementations of space-code correlator beamformer for smart antennas , 2010 .

[28]  M. Brysbaert.  Algorithms for randomness in the behavioral sciences: A tutorial , 1991 .

[29]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[30]  Mehmet Ali Çavuslu,et al.  FPGA implementation of neuro-fuzzy system with improved PSO learning , 2016, Neural Networks.