On linear programming, neural network design, pattern classification and Polynomial time training

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

Abstract

Polynomial time training and network design are two major issues for the neural network community. A new algorithm has been developed that can both "design" an appropriate network and "train" it in polynomial time. Network design is no longer a black art. The algorithm is for classification problems and uses linear programming formulations in designing and training the network. This paper will summarize the new algorithm.

Original languageEnglish (US)
Title of host publicationConference B
Subtitle of host publicationPattern Recognition Methodology and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5-8
Number of pages4
Volume2
ISBN (Print)0818629150
DOIs
StatePublished - Jan 1 1992
Event11th IAPR International Conference on Pattern Recognition, IAPR 1992 - The Hague, Netherlands
Duration: Aug 30 1992Sep 3 1992

Other

Other11th IAPR International Conference on Pattern Recognition, IAPR 1992
CountryNetherlands
CityThe Hague
Period8/30/929/3/92

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'On linear programming, neural network design, pattern classification and Polynomial time training'. Together they form a unique fingerprint.

  • Cite this

    Roy, A. (1992). On linear programming, neural network design, pattern classification and Polynomial time training. In Conference B: Pattern Recognition Methodology and Systems (Vol. 2, pp. 5-8). [201709] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.1992.201709