How can I turn off the activation of a single unit in deep neural networks?

1 次查看（过去 30 天）
Jae Son Jang
Jae Son Jang 2020-7-3
回答： Mahesh Taparia 2020-7-13
In the Deep Learning Toolbox, how can I turn off the activation of a single unit in one layer and then calculate the activation of the whole network?
As an indirect method, I think that it can be done if I set all the convolutional weights between the unit and the next layer to be 0.
However, I wonder if there is any function developed for this ablation test.

请先登录，再回答此问题。

回答（1 个）

Mahesh Taparia
Mahesh Taparia 2020-7-13
Hi
You can create a custom activation function in MATLAB and can keep the particular unit as same and for the rest of the nodes, you can apply any function. You can refer here for more information on it. Change the predict function in that class according to your requirement. Hope it will help!

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


版本

R2020a

Community Treasure Hunt

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

Start Hunting!

Translated by