# BACK PROPAGATION FOR NEURAL NETWORK MAKING DECISION

Status
Not open for further replies.

#### aqua_25

##### Newbie level 1
Hello to everybody! I study to college and it's the first time that i work with neural networks. I have to do a project (a simple one though) for making decisions. In general i think i am doing well. My project has to do with an example of a bank giving or not lawns to customers. I have 4 inputs coded for low(2) and high(3) solvency, income etc. For example maybe a customer has high income but low solvency. Anyway, this is my training set. As i have to use a step function i found hardlim in matlab. But i have a problem using it. My code is:
I=[2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3;2 2 2 2 3 3 3 3 2 2 2 2 3 3 3 3; 2 2 3 3 2 2 3 3 2 2 3 3 2 2 3 3;2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3];
O=[0 0 0 0 0 0 0 1 0 0 0 1 0 1 1 1];
net=newff([2 3;2 3;2 3;2 3;],[4,1],{'hardlim','hardlim'},'traingd');
net.traiParam.epochs=2000;
net.trainParam.goal=0.001;
net.trainParam.show=200;
net.trainParam.lr=0.05;
[net,tr]=train(net,I,O);
I am really stuck and if anyone could help me i would really appreciate it. You can either answer me here or my e-mail jpapa_jpapa@yahoo.com. Thank you all even for reading my problem.

Status
Not open for further replies.