2-Class Problem with patternnet

2013 12 13
1 个回答
回答已采纳
更新时间：2013 12 15
4 次查看（30 天）

0 个投票

Hej, I have a problem. Using the NN toolbox a neural network shall be trained to recognize a two class problem. I used the default settings ( dividerand , 10 hidden neurons, divide radio 0.7, 0.15, 0.15) and my input is a 3xn matrix and my target is a 2xn matrix ([0; 1] for class one and [1; 0] for class two for each sample), where n=21000. the ratio of the classes are about 3:2.
Why my confusion matrix looks like:
Thank you very much!!

请先登录，再回答此问题。

 采纳的回答

Greg Heath
Greg Heath 2013-12-13
编辑：Greg Heath 2013-12-14

1 个投票

Class 1 target should be [1;0] and class 2 should be [0;1]
N1 = 13840, N1trn = 9421, N1val = 2044, N1tst = 2015
N2 = 7895, N2trn = 5542, N2val = 1162, N2tst = 1191
All inputs except one class2 validation vector are classified as class 1
The confusion matrix format could be revised to make it easier to understand.
Thank you for formally accepting my answer.
Greg

2 个评论
显示 无 隐藏 无

Michael Dorner
Michael Dorner 2013-12-14
编辑：Michael Dorner 2013-12-14
Thank you for answering. Unfortunately, I tried it with 50:50 data, but still the same result. The second (and further classes) are almost not detected, but they should, at least as wrong. In the sample code (e.g. iris_data) they are ok, even for two classes (although in this case the hitrate is quite bad :-) ).
Greg Heath
Greg Heath 2013-12-15
Show your code, dimensions of input and target, comments and error messages

请先登录，再进行评论。

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

产品

标签

Community Treasure Hunt

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

Start Hunting!

Translated by