feedforwardne not enough input arguments error

Dear all,

I am trying to train a neural network using a "neural network" toolbox. Each time I try to run the code on my computer I get the following error:

Not enough input arguments.

Error in minmax (line 21) if length(a)==1,a=a*ones(size(x)); end

Error in initnw>configure_layer_weight (line 109) config.range = minmax(x);

Error in initnw (line 50) out1 = configure_layer_weight(in2,in4,in5,in6);

Error in initlay>configure_layer_weight (line 118) settings = feval(initFcn,'configure',net,'LW',i,j,x);

Error in initlay (line 47) out1 = configure_layer_weight(in2,in4,in5,in6);

Error in nnet.internal.configure.layerWeight (line 26) feval(net.initFcn,'configure',net,'LW',i,j,x);;

Error in nnet.internal.configure.layer>iConfigurePreceedingLayerWeights (line 72) net = nnet.internal.configure.layerWeight(net,i,j,range);

Error in nnet.internal.configure.layer (line 25) net = iConfigurePreceedingLayerWeights(net,i,range);

Error in network/subsasgn>setLayerInitFcn (line 1136) net = nnet.internal.configure.layer(net,i,net.layers{i}.dimensions);

Error in network/subsasgn>network_subsasgn (line 187) if isempty(err), [net,err] = setLayerInitFcn(net,i,initFcn); end

Error in network/subsasgn (line 10) net = network_subsasgn(net,subscripts,v,netname);

Error in feedforwardnet>create_network (line 119) net.layers{i}.initFcn = 'initnw';

Error in feedforwardnet (line 69) net = create_network(param);

net = feedforwardnet(neurons)

Has anyone had this problem before?

Answer 1

[Greg Heath]

Your code does not look familiar. Why not just try the code in the help and doc documentation of FITNET (regression/curvefitting) or PATTERNNET(classification/pattern-recognition)

Also see examples in both the NEWSREADER and ANSWERS using

 greg fitnet
or
 greg patternnet

Hope this helps.

Thank you for formally accepting my answer

Greg