How to apply Back propagation for 3 class problem?
显示 更早的评论
Hello. I want to solve a classification problem with 3 classes using multi layer neural network with back propagation algorithm. I'm using matlab 2012a. I'm facing trouble with newff function. I want to build a network with one hidden layer and there will be 3 neurons in the output layer, one for each class. Please advise me with example. Thanks.
采纳的回答
Greg Heath
2012-7-31
0 个投票
Newff is obsolete. Switch to fitnet for regression and curve fitting and patternnet for pattern recognition and classification.
help patternnet.
doc patternnet.
Use zscore or mapstd to standardize inputs. Use tansig, softmax, and trainscg with columns of eye(3) as targets. Use trial and error to find a suitale value for H, the number of hidden nodes.
See all of the documentation, examples and demos for patternnet, fitnet and feedforward net (replacing newpr, newfit and newff)
Hope this helps.
Greg
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 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 
