| Akaike, H. (1986). Use of Statistical Models for Time Series Analysis. In Proceedings ICASSP 86, pages 3147--3155, Tokyo. IEEE. |
....the training error and the network complexity. One technique to reach this tradeoff is to minimize a cost function composed of two terms: the ordinary training error, plus some measure of the network complexity. Several such schemes have been proposed in the statistical inference literature [see (Akaike, 1986; Rissanen, 1989; Vapnik, 1989) and references therein] as well as in the NN literature (Rumelhart, 1988; Chauvin, 1989; Hanson and Pratt, 1989; Mozer and Smolensky, 1989) Various complexity measures have been proposed, including Vapnik Chervonenkis dimensionality (Vapnik and Chervonenkis, 1971) ....
Akaike, H. (1986). Use of Statistical Models for Time Series Analysis. In Proceedings ICASSP 86, pages 3147--3155, Tokyo. IEEE.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC