Title :
Evolutionary Neural Network parallelization with multicore systems on chip
Author :
Majid, Mohammad Wadood ; Mirzaei, Golrokh ; Jamali, Mohsin M.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of Toledo, Toledo, OH, USA
Abstract :
Evolutionary Neural Network (ENN) has attracted great attention among the researchers in recent years because of its effectiveness at function optimization and, its efficiency in searching large and complex spaces to find nearly global optima. In this work, Parallel Evolutionary Neural Network algorithm is proposed and implemented on Multi-core system on chip. The algorithm is parallelized, partitioned, mapped, and scheduled on multicore. The algorithm is also implemented on single core for comparison. The parallel ENN is developed in C# using .Net framework 4.0. The .Net framework offers comprehensive and flexible threads APIs that allow the efficient implementation of multithreaded applications.
Keywords :
evolutionary computation; microprocessor chips; multiprocessing systems; neural nets; parallel processing; .Net framework; API thread; ENN; complex spaces; function optimization; global optima; multicore systems on chip; multithreaded applications; parallel evolutionary neural network algorithm; Algorithm design and analysis; Biological cells; Feeds; Genetic algorithms; Multicore processing; Neural networks; Partitioning algorithms;
Conference_Titel :
Electro/Information Technology (EIT), 2012 IEEE International Conference on
Conference_Location :
Indianapolis, IN
Print_ISBN :
978-1-4673-0819-9
DOI :
10.1109/EIT.2012.6220701