MATLAB Answers

Pattern Recongnition Network: Class balancing

2 views (last 30 days)
Thanujan Mohanadasan
Thanujan Mohanadasan on 26 Sep 2017
Hi,
How do I consider class balancing in a patternnet similar to the following example?

Answers (1)

Niraj Gadakari
Niraj Gadakari on 29 Sep 2017
You can specify the performance function in patternnet as crossentropy, and specify the performance weights to perform class balancing in Pattern Recognition Network.
  3 Comments
Nick Van Berckelaer
Nick Van Berckelaer on 20 Aug 2018
Can you provide instructions on or an example of how performance weights are to be specified during training? The parameter perfWeights is not a performParam as far as I see.
net = feedforwardnet(10);
net.performFcn = 'crossentropy';
net.performParam.regularization = 0.1;
net.performParam.normalization = 'none';

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!