ann_FF_run — run patterns trough a feedforward net.
y Matrix of outputs, one pattern per column. Each column have a correspondent column in x. x Matrix of input patterns, one pattern per column. 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. W The weight hypermatrix (initialized first trough ann_FF_init). l Defines the "injection" layer and the output layer. x patterns are injected into layer l(1) as coming from layer l(1) - 1. y outputs are collected from the outputs of layer l(2). This parameter is optional, default value is [2,size(N,'c')], i.e. the whole network. Warning: l(1)=1 does not make sense. af String containing the name of activation function. This parameter is optional, default value is "ann_log_activ", i.e. logistic activation function.