Performances improvement of back propagation algorithm applied to a lane following system

In this paper, a new high-level hardware FPGA design methodology, for artificial neural networks (ANN) descriptions, is proposed. In order to speed convergence of an ANN while avoiding instability, a back-propagation algorithm (BP), employing a momentum term to train the ANN, is used. A case study of comparison, between the back propagation (BP) and back-propagation with momentum (BPM) algorithms, is proposed. Matlab is used to validate this comparison. To achieve our goal, the two proposed design algorithms are implemented using Altera Cyclone FPGA. The originality of the work resides in the experimental validation of the simulation results with a car like robot using a lane following system. Numbers of parameters like training iterations, neurons in the hidden layer are used during this analysis. The simulation results show that the ANN trained by BPM algorithm will provide better performances than that trained by simple BP algorithm. The hardware implementation using Altera chip FPGA shows that BPM algorithm consumes less resources than the standard BP algorithm.

[1]  Fakhri Karray,et al.  Implementation of a Real-Time FPGA-Based Intelligent Parallel Parking System , 2008, J. Adv. Comput. Intell. Intell. Informatics.

[2]  Luís B. Almeida,et al.  Speeding up Backpropagation , 1990 .

[3]  R. Eckmiller.  Advanced neural computers , 1990 .

[4]  Mehmet Ali Çavuslu,et al.  Neural network training based on FPGA with floating point number format and it’s performance , 2011, Neural Computing and Applications.

[5]  Insop Song,et al.  Soft-Computing-Based Embedded Design of an Intelligent Wall/Lane-Following Vehicle , 2008, IEEE/ASME Transactions on Mechatronics.

[6]  Hung T. Nguyen,et al.  Advanced obstacle avoidance for a laser based wheelchair using optimised Bayesian neural networks , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Michal Bialko,et al.  Implementation of Fuzzy Logic Controller in FPGA Circuit for Guiding Electric Wheelchair , 2012, ICAISC.

[8]  Kaoru Hirota,et al.  Journal of Advanced Computational Intelligence and Intelligent Informatics , 2014 .

[9]  N. Derbel,et al.  A neural controller for lane/wall following system , 2008, 2008 3rd International Conference on Design and Technology of Integrated Systems in Nanoscale Era.

[10]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[11]  Mohamed Masmoudi,et al.  Optimum Architecture of Neural Networks lane following system , 2012 .

[12]  M. Bialko,et al.  Implementation of parallel fuzzy logic controller in FPGA circuit for guiding electric wheelchair , 2008, 2008 Conference on Human System Interactions.