[Master Index] [Index for export/lyngby]

lyngby_nn_qtrain

(export/lyngby/lyngby_nn_qtrain.m)


Function Synopsis

[E, Y, VOut, WOut] = lyngby_nn_qtrain(X, T, VOld, WOld, Reg, ...

Help text

 lyngby_nn_qtrain     - Quadratic neural network, training 

	function [E, Y, VOut, WOut] = lyngby_nn_qtrain(X, T, VOld, ...
	          WOld, Reg, 'PropertyName', 'PropertyValue')

	Input:	  X      Neural network input
                 T      Target output 
		  VOld   Old input weights
		  WOld   Old output weights
                 Reg    Regularization (weight decay)

       Property: MaxIteration  Iteration stop criterion
                 MinCost       Iteration stop criterion
                 MinGradient   Iteration stop criterion
                 Method        Optimization type
                 WeightAcc     [ {off} | on ] Accumulate weights
                 Info          [ {0} | ~0 ] Reporting of
                                  costfunction and gradient

	Output:	  E      Entropic error without regularization term
		  Y      Computed Outputs
		  WOut   New trained output weights or accumulated
		         weights (depending on 'WeightAcc')
		  VOut   New trained hidden weights or accumulated
		         weights (depending on 'WeightAcc')

       This function trains a neural network, either pruned or fully
       connected. It will continue until one of the stop criterions
       are meet: maxIteration is the number of epochs (optimization
       steps), minCost is the highest acceptable value for the cost
       function, minGradient is the highest acceptable value for the
       norm of the gradient.
   
       See also LYNGBY, LYNGBY_NN_QMAIN, LYNGBY_NN_QFORWARD,
                LYNGBY_NN_QERROR. 

 $Id: lyngby_nn_qtrain.m,v 1.12 2008/06/04 10:23:46 fn Exp $

Cross-Reference Information

This function calls
This function is called by

Produced by mat2html on Wed Jul 29 15:43:40 2009
Cross-Directory links are: OFF