How to write our own Loss function in Deep neural network layers.

19 次查看（过去 30 天）
Haleema Sadia
Haleema Sadia 2021-10-27
回答： Mohammad Sami 2021-10-29
I have to implement this unsupervised DNN network and a loss function given in figures. How I can introduce this loss function into my last layer in Matlab? Anycan can please guide.

请先登录，再回答此问题。

采纳的回答

Mohammad Sami
Mohammad Sami 2021-10-29
You can first check if the loss function is already available in Matlab here.
https://www.mathworks.com/help/deeplearning/ug/define-custom-training-loops-loss-functions-and-networks.html#mw_1e1e702a-95f2-411a-a85c-b2060c2a5734
If its not available you can create your own custom loss function by creating a Classification or Regression layer based on the following tutorial.
https://www.mathworks.com/help/deeplearning/ug/define-custom-classification-output-layer.html
https://www.mathworks.com/help/deeplearning/ug/define-custom-regression-output-layer.html

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 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