Why neural network gives negative output ?

2 次查看（过去 30 天）

Harsha M V 2019-3-31

评论： Greg Heath 2019-4-4

I have 15000 dataset, 6 inputs and 12 outputs. Using feedforward net, I get training, validation, test and over all regression above 95%.

But when I check trained net with new inputs, I get negative values in the outputs.

(There is no negative values in the dataset)

What is the reason for it?

What could be the worng?

What should I do to overcome this issue?

Greg Heath 2019-4-1

How different is the new data (e.g., Mahalanobis distance)?

If you know the true outputs, how do the error rates compare?

If you want positive outputs, use a sigmoid in the output layer.

Hope this helps.

*Thank you for formally accepting my answer*

Greg

Harsha M V 2019-4-4

Yes, the mahal distance is 6.5

Greg Heath 2019-4-4

It is not uncommon for new data to lie outside the bounds of training data.

Take into account whether negative values have meaning.

If not, use sigmoids in the output layer.

Greg

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

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

Translated by