{"title":"Neural Network Implementation Using FPGA: Issues and Application","authors":"A. Muthuramalingam, S. Himavathi, E. Srinivasan","volume":24,"journal":"International Journal of Electrical and Computer Engineering","pagesStart":2802,"pagesEnd":2809,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/15106","abstract":"
.Hardware realization of a Neural Network (NN), to a large extent depends on the efficient implementation of a single neuron. FPGA-based reconfigurable computing architectures are suitable for hardware implementation of neural networks. FPGA realization of ANNs with a large number of neurons is still a challenging task. This paper discusses the issues involved in implementation of a multi-input neuron with linear\/nonlinear excitation functions using FPGA. Implementation method with resource\/speed tradeoff is proposed to handle signed decimal numbers. The VHDL coding developed is tested using Xilinx XC V50hq240 Chip. To improve the speed of operation a lookup table method is used. The problems involved in using a lookup table (LUT) for a nonlinear function is discussed. The percentage saving in resource and the improvement in speed with an LUT for a neuron is reported. An attempt is also made to derive a generalized formula for a multi-input neuron that facilitates to estimate approximately the total resource requirement and speed achievable for a given multilayer neural network. This facilitates the designer to choose the FPGA capacity for a given application. Using the proposed method of implementation a neural network based application, namely, a Space vector modulator for a vector-controlled drive is presented<\/p>\r\n","references":"[1] B.Widrow and R.Winter, \"Neural nets for adaptive filtering and adaptive\r\npattern recognition \", IEEE Computer magazine,\r\npp. 25-39, March 1988.\r\n[2] K.Fukushima, S.Miyake and T.Ito, \"Neocognitron: A neural network\r\nmodel for a mechanism of visual pattern recognition\", IEEE transactions\r\non systems, Man and Cybernetics, vol.13, no.5, pp. 826-834, 1983.\r\n[3] M.Cristea, A.Dinu, \"A New Neural Network Approach to Induction\r\nMotor Speed Control\", IEEE power electronics specialist conference,\r\nvol. 2, pp. 784-788, 2001\r\n[4] S.Grossberg, E.Mingolla and D.Todorovic, \"A neural network\r\narchitecture for pre-attentive vision\", IEEE Transactions on Biomedical\r\nEngineering, vol.36, no.1, pp. 65-84, Jan 1989.\r\n[5] Leonardo Maria Reyneri \"Implementation Issues of Neuro-Fuzzy\r\nHardware: Going Towards HW\/SW Codesign\" IEEE Transactions on\r\nNeural Networks, vol.14, no.1, pp. 176-194, 2003.\r\n[6] Y.J.Chen, Du Plessis, \"Neural Network Implementation on a FPGA \",\r\nProceedings of IEEE Africon, vol.1, pp. 337-342, 2002.\r\n[7] Sund Su Kim, Seul Jung, \"Hardware Implementation of Real Time\r\nNeural Network Controller with a DSP and an FPGA \", IEEE\r\nInternational Conference on Robotics and Automation,\r\nvol. 5, pp. 3161-3165, April 2004.\r\n[8] Turner.R.H, Woods.R.F, \"Highly Efficient Limited Range Multipliers\r\nFor LUT-based FPGA Architectures\", IEEE Transactions on Very Large\r\nScale Integration Systems, Vol.15, no.10, pp. 1113-1117, Oct 2004.\r\n[9] Marchesi.M, Orlandi.G, Piazza.F, Uncini.A, \"Fast Neural Networks\r\nWithout Multipliers\", IEEE Transactions on Neural Networks, vol. 4,\r\nno.1, Jan 1993.\r\n[10] Babak Noory, Voicu Groza, \"A Reconfigurable Approach to Hardware\r\nImplementation Of Neural Networks\", Canadian Conference on\r\nElectrical and Computer Engineering, IEEE CCGEI 2003, pp. 1861-\r\n1863, 2003.\r\n[11] S.Himavathi, B.Umamaheswari \"New Membership functions for\r\neffective Design and Implementation of Fuzzy Systems\", IEEE\r\nTransactions on Systems, Man, Cybernetics, Part A, vol. 31, no.6, Nov\r\n2001.\r\n[12] Anitha \" FPGA Implementation of Estimators for sensorless control of\r\nDTC Drives\", M.Tech Thesis, Pondicherry Engg College, India, June\r\n2005.\r\n[13] B.K.Bose, Modern Power Electronics and ac drives, Pearson Education\r\n(Singapore) Pvt. Ltd., India, 2003.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 24, 2008"}