REDUCTION OF RESOURCE USAGE IN FPGA BY IMPLEMENTING BACK PROPAGATION ALGORITHM
Keywords:Field Programmable Gate Array (FPGA), Microcontrollers. Supervised Learning, VHSIC Hardware Description Language (VHDL), MATLAB.
Back propagation learning algorithm is used to implementing the FPGA for reducing the memory usage and it is one type of Supervised Learning network. The overfitting problems occurs in the device is obtained by the three steps of the algorithm. The three steps are training, validation and testing. The FPGA implementation is done by the Ex-OR functions and the VHDL code is written for the Ex-OR function using the BP algorithm. Also, the MATLAB code is written for the BP algorithm. The results show that the reducing of resource usage and increase of computational speed by the comparison of the output of VHDL code, Arduino code and MATLAB code. Both of the implementations of the Back-propagation algorithm is useful for applications to real-world problems.
 Canete.E, Chen.J, Luque.R.M, and Rubio.B, “neuralSens: A neural network based frame work to allow dynamic adaption in wireless sensor and actor networks,” J. Netw. Comput. Appl., vol. 35, no. 1, pp. 382-393, 2012.
 Dinu.A, Cirstea.M.N, and Cirstea.S.E, “Direction neural-network hardware- implemantation algorithm,” IEEE Trans. Ind. Electron., vol. 57, no. 5, pp. 1845-1848, may 2010.
 Gomperts.A, Ukil.A, and Zurfluh.F, “Development and implementation of parameterized FPGA-based general purpose neural networks for online applications,” IEEE Trans. Ind. Informat., vol. 7, no. 1, pp. 78-89, Feb. 2011.
 Gomperts.A, Ukil.A, and Zurfluh.F, “Implementation of neural network on parameterized FPGA,” in Proc. AAAI Spring Symp., Embedded Reason., 2010, pp. 45- 51.
 Hawkins.D.M, “The problem of overfitting,” J. Chem. Inf. Comput. Sci., vol. 44, no. 1, pp. 1-12, 2004.
 Huang.G.B, and Sie.C.K, “Real-time learning capability of neural networks,” IEEE Trans. Neural Netw., vol. 17, no. 4, pp. 863-878, Jul. 2006.
 Monmasson.E, Idkhajine.L, Cirstea.M, Bahri.I, Tisan.A, and Naouar.M.W, “FPGAs in industrial control applications,” IEEE Trans. Ind. Informat., vol. 7, no. 2, pp. 224-243, May 2011.
 Ortega-Zamorano.F, Jerez.J.M, Subirats.J.L, Molina.I, and Franco.L, “Smart sensor/actuator node reprogramming in changing environments using a neural network model,” Eng. Appl. Artif. Intell., vol. 30, pp. 179-188, Apr. 2014.
 Ortega-Zamorano.F, Jerez.J.M, Urda.D, Luque-Baena.R.M and Franco.L, “Efficient Implementations of the algorithm in FPGA and microcontroller,” IEEE Trans. Nerual Netw, vol. 27, no. 9, pp. 1840-1850, Sep. 2016.
Authors need to sign following agreement with International Journal of MC Square Scientific Research before publishing their articles:
- Authors need to return copyright form to Journal Editor-in-chief to proceed their articles for publication. Meantime, the journal licensed under a Creative Commons Attribution License, which permits other user to distribute the work with an acknowledgement of the authors for International Journal of MC Square Scientific Research.
- Authors are also able to share their separate, additional contractual arrangements for the non-restricted contribution of the journal with an acknowledgement of publication in International Journal of MC Square Scientific Research.
- Authors are allowed and encouraged to share their work during the submission process for increasing citation and exploring to increase the paper availability in worldwide way. The Effect of Open Access.