Neural network‐based approaches for building high dimensional and quantum dynamics‐friendly potential energy surfaces

  • Sergei Manzhos
    Department of Mechanical Engineering National University of Singapore, Block EA #07–08 9 Engineering Drive 1 Singapore 117576
  • Richard Dawes
    Department of Chemistry Missouri University of Science and Technology 120C Schrenk Hall Rolla Missouri 65409‐0010
  • Tucker Carrington
    Department of Chemistry Queen's University 90 Bader Lane Kingston Ontario Canada K7L 3N6

書誌事項

公開日
2014-10-06
権利情報
  • http://onlinelibrary.wiley.com/termsAndConditions#vor
DOI
  • 10.1002/qua.24795
公開者
Wiley

この論文をさがす

説明

<jats:p>Development and applications of neural network (NN)‐based approaches for representing potential energy surfaces (PES) of bound and reactive molecular systems are reviewed. Specifically, it is shown that when the density of <jats:italic>ab initio</jats:italic> points is low, NNs‐based potentials with multibody or multimode structure are advantageous for representing high‐dimensional PESs. Importantly, with an appropriate choice of the neuron activation function, PESs in the sum‐of‐products form are naturally obtained, thus addressing a bottleneck problem in quantum dynamics. The use of NN committees is also analyzed and it is shown that while they are able to reduce the fitting error, the reduction is limited by the nonrandom nature of the fitting error. The approaches described here are expected to be directly applicable in other areas of science and engineering where a functional form needs to be constructed in an unbiased way from sparse data. © 2014 Wiley Periodicals, Inc.</jats:p>

収録刊行物

被引用文献 (2)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ