An Efficient Parallel Algorithm for LISSOM Neural Network
Resource
Parallel Computing 28(11),1611-1633
Journal
Parallel Computing
Pages
1611-1633
Date Issued
2002-11
Date
2002-11
Author(s)
Chang, Li-Chiu
Abstract
We present a parallel algorithm for laterally interconnected synergetically self-organizing map (LISSOM) neural network, a self-organizing map with lateral excitatory and inhibitory connections, to enhance the computational efficiency. A general strategy of balancing workload for different sizes of LISSOM networks on parallel computers is described. The parallel algorithm of LISSOM is implemented on IBM SP2 and PC cluster. The results demonstrate the efficiency of this LISSOM parallel algorithm in processing networks with large sizes. Parallel implementation for different input dimensions in networks of the same size (i.e., 20×20) show that the speedup can sustain at a high level. We demonstrate the LISSOM can be applied to complex problems through the parallel algorithm devised in this study.
Subjects
Laterally interconnected synergetically self-organizing map
Parallel neural networks
Parallel implementation
Balancing load
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
14.pdf
Size
804.56 KB
Format
Adobe PDF
Checksum
(MD5):2cb17916f49fcf5d7d56be59ebdbaa16