Would you please help me?

I do have a problem about mean square error (MSE) in Neural network

Toolbox.

When I use

net=newff(minmax(pn),[10,1],{'tansig','tansig'},'traingd'),

to train the training samples, and test with testing samples to get

the optimal network (minimum MSE). The MSE value is a bit different.

How can I get the same value of mean square error for each time

running by the same network?

One of my friend said I should manually set initial weight and bias

as close as zero. After I tried, it turns out to be that the MSE

values of each network (different hidden node and epoch) are not

different at all. I don know what else did I miss.

Please help

The net automatically uses rand to initialize the weights

Set the random number generator to the same initial state.

help rand

Hope this helps.

Greg

1. How can I create a neural network for data classification using the Neural Network Toolbox?

2. Please Help: Ridge Estimator and MSE (Mean Square Error)

3. linest - cubic looking for MSE Mean Square Error

4. Neural Networks Toolbox->Time Delayed Reccurent Nerual Network problem!

5. squared mean vs. mean squared

6. Neural Network Toolbox - ERROR: Scalar cell array indices required in this assignment.

7. neural network toolbox error

8. Using Neural Network ToolBox in MATLAB for Economic Dispatch Problem !!!

9. mcc problem with neural network toolbox

10. Som toolbox (neurol network)(neural network clustering)

11. Problem with nntool and nftool (neural networks toolbox)

12. GUI and Neural Network Toolbox Problem

13. Neural Network Toolbox: Train command problem

14. a very simple model of neural net in neural toolbox - how to start ?

2 post • Page:**1** of **1**