out of memory while training pattern recognition neural network

Hi all, I am using MATLAB Version: 7.14.0.739 (R2012a) Neural Network Toolbox Version 7.0.3 (R2012a)

I am using the pattern recognition nn

• input is 315x5400
• output is 6x5400
• 1 hiddenlayer is 1500

my PC has 32 GB, using Windows 7 64 bit, with page file 32 GB

when using the supplied GUI interface to training the network, everything works fine. then when I use the same GUI to generate the script after this, then try to run the script with the same configuration used during GUI training I get the following error:

************************************************************************* % Train the Network [net,tr] = train(net,inputs,targets); 46 [net,tr] = train(net,inputs,targets); Out of memory. Type HELP MEMORY for your options.

Error in C:\Program Files\MATLAB\R2012a\toolbox\nnet\nnutils\+nnprop\jac_s.p>reprowint (line 354)

Error in C:\Program Files\MATLAB\R2012a\toolbox\nnet\nnutils\+nnprop\jac_s.p>jac_s (line 244)

Error in staticderiv>calc_jacobian (line 222) jWB = nnprop.jac_s(net,data.P,data.Pd,data.Zb,data.Zi,data.Zl,...

Error in staticderiv (line 85) out1 = calc_jacobian(in2,in3,in4);

Error in defaultderiv>calc_jacobian (line 217) jWB = staticderiv('jacobian',net,data,fcns);

Error in nntraining.perfs_jejj>calc_Y_trainPerfJeJJ (line 87) Jwb_y = fcns.deriv.calc_jacobian(net,signals,fcns);

Error in nntraining.perfs_jejj>singlecalc (line 58) [Y,trainPerfy,trainN,JEy,JJy] = calc_Y_trainPerfJeJJ(net,data,fcns);

Error in nntraining.perfs_jejj (line 9) [trainPerfy,trainN,valPerfy,~,testPerfy,~,JEy,JJy] = singlecalc(net,data,fcns);

Error in trainlm>train_network (line 199) [perf,vperf,tperf,je,jj,gradient] = nntraining.perfs_jejj(net,data,fcns);

Error in trainlm (line 113) [net,tr] = train_network(net,tr,data,fcns,param);

Error in network/train (line 106) [net,tr] = feval(net.trainFcn,net,X,T,Xi,Ai,EW,net.trainParam);

Error in autoscript2400 (line 46) [net,tr] = train(net,inputs,targets);

*********************************************************************

your help is really appreciated and looking forward to hearing from you. let me know if you need any further information.

[Greg Heath]

You mean further information like

1. Which network?

2. Size of input and output matrices?

3. Did you consult

help trainlm

doc trainlm

w.r.t. memory problems?

[Khalid Tobji]

Hi Greg I am using the pattern recognition nn

input is 315x5400

output is 6x5400

1 hiddenlayer is 1500

my PC has 32 GB, using Windows 7 64 bit, with page file 32 GB

I have tried to consult many sources but nothing so far. I am new in Matlab NN toolbox so I appreciate your help

[Greg Heath]

Please answer questions 1 & 3.