首页   按字顺浏览 期刊浏览 卷期浏览 PARALLELISM IN NEURAL NETS
PARALLELISM IN NEURAL NETS

 

作者: D. AL-DABASS,   P. VINDLACHERUVU,   D. J. EVANS,  

 

期刊: Parallel Algorithms and Applications  （Taylor Available online 1997）
卷期: Volume 11, issue 3-4  

页码: 169-185

 

ISSN:1063-7192

 

年代: 1997

 

DOI:10.1080/10637199708915593

 

出版商: Taylor & Francis Group

 

关键词: Artificial Neural Networks (ANNs);neuron;synapse;training set;teaching;parallelism

 

数据来源: Taylor

 

摘要:

This paper examines the structure of artificial neural networks (ANN) and the operation of their algorithms in order to identify the forms of parallelism that may be inherent in them. Parallelism within the topological structure of ANNs are seen to be of two forms: neuron and synapse. Operational parallelism is also of two forms: training set parallelism and recall/teaching parallelism. Performance models are formulated to predict the likely speed improvement achieved due to parallelism.

 

点击下载:  PDF (224KB)



返 回