Name

ann_FF_init — initialize the weight hypermatrix.

CALLING SEQUENCE

W = ann_FF_init(N[,r,rb])

PARAMETERS

N Row vector describing the number of neurons per layer. N(1) is the size of input pattern vector, N(size(N,'c')) is the size of output pattern vector (and also target). r Two component row vector defining the smallest and the largest value for initialization. Weights will be initialized with random numbers between these two values. r(1) the lower limit r(2) the upper limit This parameter is optional, default value is [-1,1]. rb Same as r but for biases. This parameter is optional, default value is [0,0], i.e. the biases are initialized to zero. W The weight hypermatrix, in the format used by ann_FF_Std, ann_BP_run and all other algorithms for feedforward nets (with biases).

Description

This function builds the weight hypermatrix according to network description N. Its format is detailed in ANN_FF.

See Also

ANN , ANN_FF