Changing performance function of neural network to root mean square error.

3 次查看（过去 30 天）
Onkar Khadke
Onkar Khadke 2020-10-7
评论： Onkar Khadke 2020-10-13
Hello,
In neural network, how can we stop the training by telling the network to stop once the root mean square error between target values and output from the network falls below say 0.01 or 0.001 ? I am specifically asking with respect to Levenberg Marquardt algorithm, such that how can we change the performance function to rmse(root mean square error)

请先登录，再回答此问题。

采纳的回答

Pranav Verma
Pranav Verma 2020-10-13
Hi Onkar,
Please refer to the below discussion on the same lines:
https://www.mathworks.com/matlabcentral/answers/441253-when-i-should-stop-training-a-neural-network
  1 个评论
Onkar Khadke
Onkar Khadke 2020-10-13
Thank you P. Verma sir. I refered to what you said. I understood how to avoid over training the network. So in trainlm the default performance function used is mse(mean squared error) and we cannot change this to rmse (root mean squared error) ?

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by