Pattern Recongnition Network: Class balancing
1 回表示 (過去 30 日間)
古いコメントを表示
Hi,
How do I consider class balancing in a patternnet similar to the following example?
0 件のコメント
回答 (1 件)
Niraj Gadakari
2017 年 9 月 29 日
You can specify the performance function in patternnet as crossentropy, and specify the performance weights to perform class balancing in Pattern Recognition Network.
3 件のコメント
Nick Van Berckelaer
2018 年 8 月 20 日
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';
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!