• DocumentCode
    1684062
  • Title

    Finding relevant knowledge: KBCC applied to DNA splice-junction determination

  • Author

    Thivierge, Jean-Philippe ; Shultz, Thomas R.

  • Author_Institution
    Dept. of Psychol., McGill Univ., Montreal, Que., Canada
  • Volume
    2
  • fYear
    2002
  • fDate
    6/24/1905 12:00:00 AM
  • Firstpage
    1401
  • Lastpage
    1405
  • Abstract
    Knowledge-based cascade-correlation (KBCC) was applied to splice-junction determination using biological rules as prior knowledge. Since not all rules are recruited, KBCC is useful in assessing relevant CC sources. Fewer recruits are required than CC. However, KBCC does not outperform CC on learning speed and accuracy, due to limited relevancy of some sources
  • Keywords
    DNA; biology computing; correlation methods; knowledge based systems; learning (artificial intelligence); neural nets; DNA splice-junction; biology computing; knowledge-based cascade-correlation; learning; machine learning; neural networks; relevancy; Amino acids; DNA; Humans; Knowledge management; Network topology; Neural networks; Psychology; Quality management; Recruitment; Sequences;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
  • Conference_Location
    Honolulu, HI
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-7278-6
  • Type

    conf

  • DOI
    10.1109/IJCNN.2002.1007721
  • Filename
    1007721