Parallel, self-organizing, hierarchical neural networks. II

Author

Ersoy, Okan K. ; Hong, Daesik

Author_Institution

Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA

Volume

40

Issue

2

fYear

1993

fDate

4/1/1993 12:00:00 AM

Firstpage

218

Lastpage

227

Abstract

For pt.I see IEEE Trans. Neural Networks, vol.1, p.167-78 (1990). Parallel, self-organizing, hierarchical neural networks (PSHNNs) involve a number of stages with error detection at the end of each stage, i.e., rejection of error-causing vectors, which are then fed into the next stage after a nonlinear transformation. The stages operate in parallel during testing. Statistical properties and the mechanisms of vector rejection of the PSHNN are discussed in comparison to the maximum likelihood method and the backpropagation network. The PSHNN is highly fault tolerant and robust against errors in the weight values due to the adjustment of the error detection bounds to compensate errors in the weight values. These properties are exploited to develop architectures for programmable implementations in which the programmable parts are reduced to on-off or bipolar switching operations for bulk computations and attenuators for pointwise operations

Keywords

backpropagation; error detection; maximum likelihood estimation; self-organising feature maps; attenuators; backpropagation network; bipolar switching operations; error detection; hierarchical neural networks; maximum likelihood method; nonlinear transformation; parallel neural networks; programmable implementations; self-organizing; Attenuators; Backpropagation; Computer architecture; Fault detection; Fault tolerance; Maximum likelihood detection; Mechanical factors; Neural networks; Robustness; Testing;

fLanguage

English

Journal_Title

Industrial Electronics, IEEE Transactions on

Publisher

ieee

ISSN

0278-0046

Type

jour

DOI

10.1109/41.222643

Filename

222643