How to overcome poor prediction of neural network.

1 view (last 30 days)
Nitin
Nitin on 23 Apr 2014
Answered: Greg Heath on 28 Apr 2014
I have created a neural network with nftool for prediction with default settings. Data used for input is matrix of 19x1140 i.e 19 input parameter and 1x1140 i.e 1 output parameter. The regression values comes around .99 and .98 but during prediction using sim(net,test) command it gives wrong prediction. How to solve this problem?

Sign in to answer this question.

Accepted Answer

Greg Heath
Greg Heath on 28 Apr 2014
Use datadivision and as few hidden nodes as possible. Repeat multiple times to get a good set of random initial weights.
What do you mean by prediction ... the test set performance?

More Answers (0)

Categories

Find more on Function Approximation and Clustering in Help Center and File Exchange

Tags

Products

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!