Paper Info
Title
An Enhanced Parallel & Distributed Implementation of the Harmony Search Based Supervised Training of Artificial Neural Networks
Abstract
The authors have published earlier a parallel & distributed implementation method for the supervised training of feed-forward artificial neural networks using the Harmony Search algorithm. Such implementation was intended to address the training of larger pattern-classification problem. The implementation platforms included both a homogeneous and a heterogeneous system of Master-Slave processing nodes. The latter heterogeneous implementation utilized a node benchmarking score obtained via independent software in order to determine the load balancing ratios for the different processing nodes. In this paper an enhanced alternative benchmarking technique is proposed that is based on the actual workload execution times for each heterogeneous processing node. Using the same pattern-classification problem on the same heterogeneous platform setup used in the previous technique, results show that the proposed technique has attained higher speedup in comparison with the former.
Year
DOI
Venue
2011
10.1109/CICSyN.2011.65
CICSyN
Keywords
Field
DocType
different processing node,harmony search,artificial neural networks,proposed technique,heterogeneous system,heterogeneous processing node,implementation platform,master-slave processing node,implementation method,previous technique,latter heterogeneous implementation,heterogeneous platform setup,learning artificial intelligence,neural network,artificial neural network,master slave,parallel processing,parallel distributed processing,harmony search algorithm,benchmark testing,java,feed forward,load balance
Load management,Load balancing (computing),Computer science,Software,Harmony search,Artificial neural network,Benchmark (computing),Benchmarking,Distributed computing,Speedup
Conference
Citations 
PageRank 
References 
2
0.38
5
Authors
2
Name
Order
Citations
PageRank
Ali Kattan1232.46
Rosni Abdullah215624.82