Classification and verification through the combination of the multi-layer perceptron and auto-association neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

The Multi-Layer Perceptron (MLP) classifier has excellent discriminatory properties but forms open decision boundaries, which makes it inappropriate for detecting non-class data. The Auto-Association Neural Network (AANN), on the other hand, creates closed decision boundaries around the training set and is thus appropriate for detection and verification in the absence of counter-examples. However, we illustrate that AANNs may fall short in discriminating between classes that lie close to each other or are overlapping in feature space. To overcome each of the network types' weaknesses, we propose a combined system consisting of one MLP and C AANNs for C-class recognition problems. Experimental results show that we can maintain good discriminatory properties whilst reliably detecting non-class data. This is illustrated in the context of radio communication signal recognition. © 2005 IEEE.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks, IJCNN 2005
Place of PublicationNEW YORK
PublisherIEEE
Pages1166-1171
Number of pages6
Volume2
ISBN (Print)0780390482, 9780780390485
DOIs
Publication statusPublished - 2005
Event2005 International Joint Conference on Neural Networks - Montreal, QC, Canada
Duration: 31 Jul 20054 Aug 2005

Conference

Conference2005 International Joint Conference on Neural Networks
Abbreviated titleIJCNN 2005
CountryCanada
CityMontreal, QC
Period31/07/054/08/05

Fingerprint Dive into the research topics of 'Classification and verification through the combination of the multi-layer perceptron and auto-association neural networks'. Together they form a unique fingerprint.

Cite this