A New Type of Pulse Neural Network Based on FPGA

Abstract:

In this paper, based on the study analyzed on the basis of a variety of neural networks, a kind of new type pulse neural network is implemented based on the FPGA [1]. The neural network adopts the Sigmoid function as its hidden layer nonlinear excitation function, at the same time, to reduce ROM table storage space and improve the efficiency of look-up table [2], it also adopts the STAM algorithm based nonlinear storage. Choose Altera Corporation’s EDA tools Quartus II as compilation, simulation platform, Cyclone II series EP2C20F484C6 devices and realized the pulse neural networks finally. In the last, we use XOR problem as example to carry out the hardware simulation, and simulation results are consistent with the theoretical value. Neural network to improve the complex, nonlinear, time-varying, uncertainty about the system reliability and security provides a new way.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 6081-6084
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.6081
• Online since: May 2014
• Authors: Qian Huang*, Wen Long Li, Jian Kang, Jun Yang
• Keywords: FPGA, Pulse Neural Network, Sigmoid, STAM

References

[1] CAI Zixing. The principle and application of Intelligent control (first edition). Beijing: Tsinghua university press, (2007).

[2] Simon HayKin. Neural networks and machine learning (the third edition of the original book). Beijing: mechanical industry press, (2011).

[3] Dinu A, Cirstea M N, Cirstea S E. Direct Neural-Network Hardware-Implementation Algorithm. IEEE Transactions on Industrial Electronics, 2010, 57(5): 1845-1848.

DOI: 10.1109/tie.2009.2033097

[4] Shein Idelson M, Ben-Jacob E, Hanein Y. Innate Synchronous Oscillations in Freely-Organized Small Neuronal Circuits. PLoS ONE, 2010, 5(12).

DOI: 10.1371/journal.pone.0014443

[5] Himavathi S, Anitha D, Muthuramalingam A. Feed forward Neural Network Implementation in FPGA Using Layer Multiplexing for Effective Resource Utilization. IEEE Transactions on Neural Networks, 2007, 18(3): 880-888.

DOI: 10.1109/tnn.2007.891626