Ranking importance of input parameters of neural networks

Author： Balakin K.V. Korshun V.A. Mikhalev I.I. Maleev G.V. Malakhov A.D. Prokhorenko I.A. Berlin Y.A. Sung A.H.

Publisher： Elsevier

ISSN： 0957-4174

Source： Expert Systems with Applications, Vol.15, Iss.3, 1998-10, pp. : 405-411

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Related content

Adaptive neural networks for robust estimation of signal parameters

By awek Cichocki Andrzej

COMPEL: Int J for Computation and Maths. in Electrical and Electronic Eng., Vol. 19, Iss. 3, 2000-03 ,pp. : 903-912

Emerald Group Publishing Ltd

Access to resources Recommend Favorite

Fast learning artificial neural networks for continuous input applications

By Evans D.J. Tay L.P.

Kybernetes: The International Journal of Systems & Cybernetics, Vol. 24, Iss. 3, 1995-03 ,pp. : 11-23

Emerald Group Publishing Ltd

Access to resources Recommend Favorite

Inverse optimality in the class of Hopfield neural networks with input nonlinearity

By Farid Yousef

Neural Computing & Applications, Vol. 22, Iss. 3-4, 2013-03 ,pp. : 711-717

Springer Publishing Company

Access to resources Recommend Favorite

Regularizing the effect of input noise injection in feedforward neural networks training

By Seghouane Abd-Krim Moudden Yassir Fleury Gilles

Neural Computing & Applications, Vol. 13, Iss. 3, 2004-09 ,pp. : 248-254

Springer Publishing Company

Access to resources Recommend Favorite

The influence of ARIMA-GARCH parameters in feed forward neural networks prediction

By Oliveira Mauri

Neural Computing & Applications, Vol. 20, Iss. 5, 2011-07 ,pp. : 687-701

Springer Publishing Company

Access to resources Recommend Favorite