In this paper, an underlying problem on the fast BRAIN learning algorithm is pointed out, which is avoided by introducing the quantity count (∙, ∙). In addition, its speed advantage can still be enjoyed only at a cost of a little additional space. The improved fast BRAIN learning algorithm is also given.


BRAIN Numerical Computation 


  1. Aykin S. Neural Networks: A Comprehensive Foundation, 2nd Edition, Prentice-Hall, Inc., 1999.Google Scholar
  2. Goldberg D. What Every Computer Scientist Should Know about Floating-Point Arithmetic. ACM Computing Survey, 1991, 23(1): 5-48.CrossRefGoogle Scholar
  3. IEEE. IEEE Standard 754-1985 for Binary Floating-Point Arithmetic, IEEE, 1985. Reprinted in SIGPLAN, 1987, 22(2): 9-25.Google Scholar
  4. Matula D.W. and Kornerup P. Finite Precision Rational Arithmetic: Slash Number Systems. IEEE Transaction on Computers, 1985, C-34(1): 3-18.CrossRefGoogle Scholar
  5. Rampone S. An Error Tolerant Software Equipment for Human DNA Characterization. IEEE Transactions on Nuclear Science, 2004, 52(5): 2018-2026.CrossRefGoogle Scholar
  6. Rampone S. Recognition of Splice Junctions on DNA Sequence by BRAIN Learning Algorithm. Bioinformatics, 1998, 14(8): 676-684.CrossRefPubMedGoogle Scholar
  7. Vapnik V.N. Statistical Learning Theory, Wiley, New York, 1998.Google Scholar
  8. Vapnik V.N. The Nature of Statistical Learning Theory, 2nd Edition, Springer Verlag, New York, 1999.Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2008

Authors and Affiliations

  • Shuo Xu
    • 1
  • Xin An
    • 2
  • Lan Tao
    • 3
  1. 1.College of Information and EngineeringChina Agricultural UniversityChina
  2. 2.School of International Trade and EconomicsUniversity of International Business and EconomicsChina
  3. 3.College of Information EngineeringShenzhen UniversityChina

Personalised recommendations