Combining neural networks for protein secondary structure prediction

Søren Kamaric Riis

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    267 Downloads (Pure)


    In this paper structured neural networks are applied to the problem of predicting the secondary structure of proteins. A hierarchical approach is used where specialized neural networks are designed for each structural class and then combined using another neural network. The submodels are designed by using a priori knowledge of the mapping between protein building blocks and the secondary structure and by using weight sharing. Since none of the individual networks have more than 600 adjustable weights over-fitting is avoided. When ensembles of specialized experts are combined the performance is better than most secondary structure prediction methods based on single sequences even though this model contains much fewer parameters
    Original languageEnglish
    Title of host publicationIEEE International Conference on Neural Networks
    VolumeVolume 4
    Publication date1995
    ISBN (Print)07-80-32768-3
    Publication statusPublished - 1995
    Event1995 IEEE International Conference on Neural Networks - Perth, WA, United States
    Duration: 27 Nov 19951 Dec 1995


    Conference1995 IEEE International Conference on Neural Networks
    CountryUnited States
    CityPerth, WA
    Internet address

    Bibliographical note

    Copyright: 1995 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

    Fingerprint Dive into the research topics of 'Combining neural networks for protein secondary structure prediction'. Together they form a unique fingerprint.

    Cite this