Spiking Versus Traditional Neural Networks for Character Recognition on FPGA Platform

Authors

  • Amjad J. Humaidi Department of Control Systems Engineering, University of Technology, Sina'a St., Baghdad, Iraq
  • Thaer Mohammad Kadhim Department of Control Systems Engineering, University of Technology, Sina'a St., Baghdad, Iraq

Keywords:

Artificial Neural Networks (ANN), Spiking Neural Network (SNN), spike time dependent plasticity (STDP).

Abstract

Spiking Neural Networks (SNN) is considered the third generation of neural networks. This type of neural networks are inspired from biological nature of cortical neuron, and they (SNNs) introduced the concept of time rather than using real-valued inputs and outputs, which is a characteristic feature of Artificial Neural Network (ANN). The purpose of this research work is to design, develop and implementation of character recognition algorithm in a hardware environment (FPGA) based on Artificial Neural Networks and Spiking Neural Networks. Then, a comparison study is made, between these two generations of neural networks, regarding execution time and hardware size on the FPGA platform. Altera CycloneII DE2 (development and education) board has been suggested to work with for design and implementation of character learning and recognition. Coding with Verilog Language has been used for developing and synthesising the software structure of SNN and, also, to perform learning and recognition inside Altera Cyclone-II DE2 hardware. The learning method used in ANN is back propagation, while spike time dependent plasticity (STDP) has been employed for learning of SNN.

Author Biography

Amjad J. Humaidi, Department of Control Systems Engineering, University of Technology, Sina'a St., Baghdad, Iraq

department of control and systems engineering

References

G.Q. Bi and M.M Poo, "Synaptic modification in cultured hippocampal neurons: Dependence on spike timing, synaptic strength and postsynaptic cell type," J. Neuroscience, vol. 18, pp. 10462-10472, Dec.1998.

E. Adrian, the Basis of Sensation: The Action of the Sense Organs. W. W. Norton, New York, 1928.

Sergio Davies, "Learning in Spiking Neural Networks," Ph.D., Dissertation, University of Manchester, 2012.

R. Gȕtig and H. Sompolinsky, "The tempotron: a neuron that learns spike timing-based decisions," Nature neuroscience, vol. 9, no. 4, pp. 420–428, 2006.

R. Urbanczik and W. Senn, "A gradient learning rule for the tempotron," Neural Computation, vol.21, pp. 340–352, 2009.

Nikola Kasabov, " To spike or not to spike: A probabilistic spiking neuron model," Neural Network, vol.23, pp.16-19, 2010.

Izhikevich, E. M., "Simple Model of Spiking Neurons," IEEE Transactions on neural networks, vol.14, no. 6, pp.1569-1572, 2003.

Andrzej Kasinski, Filp Ponulak, "Comparison of Supervised Learning Methods for Spike Time Coding in Spiking Neural Networks," International Journal Applied Mathematics Computer Science, Vol. 16 (1), no. 1, pp.101-113, 2006.

Mariam Bokeria, "Character Recognition with Spiking Neural Networks", M.Sc. Thesis, Tallinn University of Technology, Tallinn, Estonia, 2017.

Nikolai Jefimov, "Image Recognition by Spiking Neural Networks", M.Sc. Thesis, Tallinn University of Technology, Tallinn, Estonia, 2017.

Yuan Jing, "An Efficient FPGA Implementation of Optical Character Recognition System for License Plate Recognition", M.Sc. Thesis, University of Windsor, Ontario, Canada, 2016.

S. Chaturvedi, A. A. Khurshid, and Nirja Karlewar, "ASIC Implementation for Improved Character Recognition and Classification using SNN Model", International Journal of Software and Web Sciences, Vol. 14, no. 1, pp. 13-17, 2015.

M. Moradi, M. A. Pourmina, and F. Razzazi, "FPGA-Based Farsi Handwritten Digit Recognition System", International Journal of Simulation Systems Science & Technology, vol. 11, pp. 17-22, 2010.

Ankur Gupta, Lyle Long, "Character Recognition using Spiking Neural Networks," International Joint Conference on Neural Networks, Orlando, Florida, USA, August 12-17, 2007.

Izhikevich, E. M., "Simple Model of Spiking Neurons," IEEE Transactions on neural networks, vol.14, no. 6, pp.1569- 1572, 2003.

Amjad J. Humaidi, Thaer M. Kadhim, "Recognition of English Characters Using Spiking Neural Networks," International Journal of Engineering and Technology, Vol. 9, no. 5, pp.3494-3503 Oct-Nov. 2017.

Downloads

Published

2018-08-28

How to Cite

Humaidi, A. J., & Mohammad Kadhim, T. (2018). Spiking Versus Traditional Neural Networks for Character Recognition on FPGA Platform. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 10(3), 109–115. Retrieved from https://jtec.utem.edu.my/jtec/article/view/3353