Asked by mayuresh
on 3 Dec 2012

i am doing neural network ,training the netwrk eah time gives different results.

Answer by Greg Heath
on 3 Dec 2012

Accepted answer

Training performance varies because the default train/val/test data division AND initial weights are pseudorandom.

One of many solutions for sufficiently large data sets.

1. Initialize the RNG so that the same stream of pseudorandom numbers can be repeated.

rng(0)

2. Design 10 or more nets

3. Choose the net with the smallest validation (NOT TRAINING) set error.

4. Estimate the performance on unseen data with the test set error.

5. If performance is unsatisfactory, try increasing the number of hidden nodes.

How large are X and T?

Hope this helps.

Thank you for formally accepting my answer

Greg

Greg Heath
on 7 Dec 2012

The pseudo random number generation is done automatically. However if you want to duplicate your run(s). You must intialize the geneator.

help rng

doc rng

Greg

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi test

Learn moreOpportunities for recent engineering grads.

Apply Today
## 0 Comments