Open Access. Powered by Scholars. Published by Universities.®
Electrical and Computer Engineering
Electrical and Computer Engineering Faculty Research & Creative Works
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Comparison Of Particle Swarm Optimization And Backpropagation As Training Algorithms For Neural Networks, Ganesh K. Venayagamoorthy, Venu Gopal Gudise
Comparison Of Particle Swarm Optimization And Backpropagation As Training Algorithms For Neural Networks, Ganesh K. Venayagamoorthy, Venu Gopal Gudise
Electrical and Computer Engineering Faculty Research & Creative Works
Particle swarm optimization (PSO) motivated by the social behavior of organisms, is a step up to existing evolutionary algorithms for optimization of continuous nonlinear functions. Backpropagation (BP) is generally used for neural network training. Choosing a proper algorithm for training a neural network is very important. In this paper, a comparative study is made on the computational requirements of the PSO and BP as training algorithms for neural networks. Results are presented for a feedforward neural network learning a nonlinear function and these results show that the feedforward neural network weights converge faster with the PSO than with the BP …
Evolving Digital Circuits Using Particle Swarm, Ganesh K. Venayagamoorthy, Venu Gopal Gudise
Evolving Digital Circuits Using Particle Swarm, Ganesh K. Venayagamoorthy, Venu Gopal Gudise
Electrical and Computer Engineering Faculty Research & Creative Works
Particle swarm optimization (PSO) motivated by the social behavior of organisms is proposed for evolution of combinational logic circuits. Results are presented to show that PSO based evolution of digital circuits are equivalent to or even with better solutions (with minimum number of logic gates) than that of a human designer and other genetic algorithm (GA) based techniques. This PSO based approach converges faster than other approaches reported in literature using genetic algorithms and as a result the computational intensity involved in hardware evolution is reduced. Examples taken from the literature are used to evaluate the performance of the proposed …