deep classification network with "logsig layer" instead of softmaxLayer

1 次查看（过去 30 天）

kira 2018-12-20

编辑： kira 2018-12-20

Hello,

I want to create a deep classification net, but my classes aren't mutually exclusive (what sofmaxlayer do).

Is it possible to define a non mutually exclusive classification layer (i.e., a data can be in more than one class)?

One way to do it, it would be with a logsig function in the classification layer, instead of a softmax, but I have no idea how to acomplish that....

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

R2018a

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

Translated by