Neural network approach for the investigation of chemical phenomena

Jerry A. Darsey, Bobby G. Sumpter

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

Abstract

Neural networks are coupled with other computational methods (molecular dynamics, Monte Carlo, etc.) in order to obtain information on the structure and atomistic dynamics of chemical systems. Several aspects of this research are discussed: (1) the prediction of multidimensional potential-energy surfaces from vibrational spectra and constant volume heal capacities, (2) mechanisms and rates for energy flow and redistribution, and (3) prediction of physical properties of organic and polymeric systems. The overall results obtained demonstrate the computational power and accuracies that can be achieved coupling other computational methods with neural networks, as well as providing intriguing results on the internal dynamics of chemical systems.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsMarry Lou Padgett
PublisherPubl by Society of Photo-Optical Instrumentation Engineers
Pages296-300
Number of pages5
ISBN (Print)1565550072
StatePublished - 1993
Externally publishedYes
EventProceedings of the 3rd Workshop on Neural Networks: Academic/Industrial/NASA/Defense - Alabama, AL, USA
Duration: Feb 10 1992Feb 12 1992

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume1721
ISSN (Print)0277-786X

Conference

ConferenceProceedings of the 3rd Workshop on Neural Networks: Academic/Industrial/NASA/Defense
CityAlabama, AL, USA
Period02/10/9202/12/92

Fingerprint

Dive into the research topics of 'Neural network approach for the investigation of chemical phenomena'. Together they form a unique fingerprint.

Cite this