Jackwerth, Jens Carsten (1997): Artificial Stupidity: A Reply. Published in: Journal of Portfolio Management , Vol. 27, No. 1 : pp. 120-121.
Download (17kB) | Preview
Murphy, Koehler, and Fogler  gave in the last issue of the Journal of Portfolio Management an account of how to raise a neural net’s IQ. The purpose of this reply is to point out some of the general difficulties with neural nets. Also, I would like to mention an alternative method, namely Pade approximants, which does not suffer from these difficulties.
|Item Type:||MPRA Paper|
|Original Title:||Artificial Stupidity: A Reply|
|English Title:||Artificial Stupidity: A Reply|
|Keywords:||Artifical; Stupidity; Neural Networks|
|Subjects:||C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C45 - Neural Networks and Related Topics|
|Depositing User:||Jens Jackwerth|
|Date Deposited:||19. Nov 2008 06:42|
|Last Modified:||13. Feb 2013 21:40|
Murphy, Christopher M., Gary J. Koehler, and H. Russell Fogler. “Artificial Stupidity.” Journal of Portfolio Management, Winter 1997, pp. 24-29.
Press, William H., Saul A. Teukolsky, William T. Vetterling, and Brian P. Flannery. Numerical Recipes in FORTRAN: the art of scientific computing, 2nd. Ed. Cambridge: Cambridge University Press, 1992.