Abstract
In this paper, two-layered feed forward artificial neural network’s (ANN) training by back propagation and its implementation on FPGA (field programmable gate array) using floating point number format with different bit lengths are remarked based on EX-OR problem. In the study, being suitable with the parallel data-processing specification on ANN’s nature, it is especially ensured to realize ANN training operations parallel over FPGA. On the training, Virtex2vp30 chip of Xilinx FPGA family is used. The network created on FPGA is coded by using VHDL. By comparing the results to available literature, the technique developed here proved to consume less space for the subjected ANN training which has the same structure and bit length, it is shown to have better performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Haykin S (1994) Neural networks a comprehensive foundation. Macmillan College Publishing, Englewood Cliffs
Narendra KS, Parthasaraty K (1990) Identification and control of dynamical systems using neural networkworks. IEEE Trans Neural Netw 1(1):4–27
Farrugia S, Yee H, Nickolls P (1993) Implantable cardioverter defibrillator electrogram recognition with a multiplayer perceptron. PACE: Pacing Clin Electrophysiol 16(1):228–234
Çavuşlu MA, Karakaya F, Altun H (2008) ÇKA Tipi Yapay Sinir Aği Kullanılarak Plaka Yeri Tespitinin FPGA’da Donanımsal Gerçeklenmesi. In: Proceedings of Akıllı Sistemlerde Yenilikler ve Uygulamalar Sempozyumu 2008 (ASYU 2008) Isparta, Turkey (in Turkish)
Ramache U (1992) SYNAPSE: a neurocomputer that synthesize neural algorithms on paralel systolic engine. J Parallel Distrib Comput 14:306–318
Burr J (1993) Digital neurochip design. In: Przytula KW, Prasanna VK (eds) Parallel digital implementations of neural networks. Prentice Hall, Englewood Cliffs, pp 223–281
Rucket U, Funke A, Pintake C (1993) Acceleratorboard for neural associative memories. Neurocomputing 5(1):39–49
Morgan P, Ferguson A, Bolouri H (1994) Cost-performance analysis of FPGA, VLSI and WSI implementations of a RAM-based neural network. In: Proceedings of the 4th international conference on microelectronics for neural networks and fuzzy systems. Turin, Italy, pp 235-243
Krips M, Lammert T, Kummert A (2002) FPGA implementation of a neural network for a real-time hand tracking system. In: Proceedings of the first IEEE international workshop on electronic design, test and applications. pp 313–317
Ossoinig H, Reisinger E, Steger C, Weiss R (1996) Design and FPGA-implementation of a neural network. In: Proceedings of the 7th international conference on signal processing applications & technology. Boston, USA, pp 939–943
Sahin S, Becerikli Y, Yazici S (2006) Neural network implementation in hardware using FPGAs. Lect Notes Comput Sci 4234:1105–1112
Zhu J, Milne GJ, Gunther BK (1999) Towards an FPGA based reconfigurable computing environment for neural network implementations. 9th international conference on artificial neural networks:ICANN’99 Edinburgh UK, IEE Conf Pub 2(CP470):661–666. doi:10.1049/cp:19991186
Mousa M, Areibi S, Nichols K (2006) On the arithmetic precision for implementing back-propagation networks on FPGA: a case study. In: Omondi AR, Rajapakse JC (eds) FPGA implementations of neural networks. Springer, US, pp 37–61
Savich AW, Moussa M, Areibi S (2007) The impact of arithmetic representation on implementing MLP-BP on FPGAs: a study. IEEE Trans Neural Netw 18(1):240–252
Haykin S (1999) Neural networks a comprehensive foundation, 2nd edn. Prentice Hall, NJ
Stevenson M, Winter R, Widrow B (1990) Sensitivity of feedforward neural networks to weight errors. IEEE Trans Neural Netw 1(1):71–80
Çavuşlu MA, Karakuzu C, Şahin S (2006) Neural network hardware implementation using FPGA. In: ISEECE 2006 3rd international symposium on electrical, electronic and computer engineering symposium proceedings. TRNC, Nicosia, pp 287–290
Az I, Şahin S, Karakuzu C, Çavuşlu MA (2006) Implementation of FFT and IFFT Algorithms in FPGA. In: ISEECE 2006 3rd international symposium on electrical, electronic and computer engineering symposium proceedings. TRNC, Nicosia, pp 7–10
Çavuşlu MA, Dikmeşe S, Sahin S, Küçük K, Kavak A (2006) Akıllı Anten Algoritmalarının IEEE 754 Kayan Sayı Formatı ile FPGA Tabanlı Gerçeklenmesi ve Performans Analizi. In: Proceedings of URSI-TÜRKİYE’ 2006 3. BİLİMSEL KONGRESİ. Ankara, Turkey, pp 610–612 (in Turkish)
Az I, Sahin S, Cavuslu MA (2007) Implementation of fast fourier and inverse fast fourier transforms in FPGA. In Proceedings of IEEE 15th signal processing and communications applications SIU 2007. Eskisehir, Turkey, pp 1–4
Belanovic P (2002) Library of parameterized hardware modules for floating-point arithmetic with an example application. Dissertation, Northeastern University
Elliot D L (1993) A better activation function for artificial neural networks. Technical Research Report T.R. 93-8, Institute for Systems Research, University of Maryland
Tveter DR (1998) Backpropagator’s Review. http://www.dontveter.com/bpr/activate.html. Accessed 28 May 2010
Gallagher S (2004) Accelerating DSP Algorithms Using FPGAs. http://klabs.org/mapld04/presentations/session_p/p188_gallagher_s.ppt. p 6, Accessed 28 May 2010
Vishwanathan A, FPGA implementation of network printer (an overview). http://www25.brinkster.com/anandv98/projects/nwprinter.asp. Accessed 28 May 2010
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Çavuşlu, M.A., Karakuzu, C., Şahin, S. et al. Neural network training based on FPGA with floating point number format and it’s performance. Neural Comput & Applic 20, 195–202 (2011). https://doi.org/10.1007/s00521-010-0423-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-010-0423-3