Neural Network Validation Index

1 次查看（过去 30 天）
Auston
Auston 2014-8-15
回答： Greg Heath 2015-2-1
When I initialize my network I include the standard 70% training, 15% validation, and 15% testing indices with their respective variable (network.divideParam.trainInd / valInd / testInd). However after training there is no information for the validation. It appears that the validation indices were appended to the training indices.
My network variables appear as follows: network.divideParam.valInd = [1 x 238140] network.userdata.trainingRecord.valInd = []
Why would there be no validation information in the training record?

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2015-2-1
You may be using trainbr.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Function Approximation and Nonlinear Regression 的更多信息

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by