How to solve the issues during trainining in ohr?

1 次查看(过去 30 天)
Hi,
I am doing project on Offline handwritten character recognition.I have successfully completed till feature extraction.I have tried neural network(FF,RBF,Patternnet etc), SVM for training.But i didn't get exact result. Got out of memory error when i have tried feedforward etc .I have got 96% accuracy for RBF during training but got very poor results during testing.I have spend nearly 1 month for training.Now I’m on a dead line with my projects date. I don't know what to do.Could any body help me please............
  1 个评论
Greg Heath
Greg Heath 2013-5-21
How many characters? How many extracted features? What kind of data normalization? What kind of input dimensionality reduction? Are the targets columns from a unit matrix? What kind of trn/val/tst data division? What was your training goal? What kind of performance is obtained in te literature for tis kind of problem?
When you used PATTERNNET how did you choose the number of hidden nodes, H?
[ I N ] = size(inputs) = ?
[ O N ] = size(targets) = ?
Post your patternnet code.

请先登录,再进行评论。

回答(0 个)

类别

Help CenterFile Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by