A two-level learning hierarchy for constructing incremental projection generalizing neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

One of the incremental learning-based neural networks that theoretically guarantees the optimal generalization capability and provides exactly the same generalization capability as that obtained by batch learning is incremental projection generalizing neural networks. This paper will describe a two-level learning hierarchy for constructing the networks. An incremental projection learning in neural networks algorithm is employed at the lower level to construct the network while the learning parameters, the orders of the reproducing kernel Hilbert space, are optimized using a genetic algorithm at the upper level. The networks produced by this learning hierarchy will be used as subsystem of the artificial odor discrimination system to approximate percentage of alcohol.

Original languageEnglish
Title of host publicationProceedings - APCCAS 2002
Subtitle of host publicationAsia-Pacific Conference on Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages541-546
Number of pages6
ISBN (Electronic)0780376900
DOIs
Publication statusPublished - 2002
EventAsia-Pacific Conference on Circuits and Systems, APCCAS 2002 - Denpasar, Bali, Indonesia
Duration: 28 Oct 200231 Oct 2002

Publication series

NameIEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS
Volume2

Conference

ConferenceAsia-Pacific Conference on Circuits and Systems, APCCAS 2002
Country/TerritoryIndonesia
CityDenpasar, Bali
Period28/10/0231/10/02

Keywords

  • Artificial neural networks
  • Genetic algorithms
  • Hilbert space
  • Kernel
  • Mathematics
  • Neural networks
  • Neurons
  • Radio access networks
  • Resource management
  • Sampling methods

Fingerprint

Dive into the research topics of 'A two-level learning hierarchy for constructing incremental projection generalizing neural networks'. Together they form a unique fingerprint.

Cite this