Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.
Hidden Layer Activation Functions
In H2o deep learning operator I can set the hidden layer size and the activation function. Is there a way to assign different activation functions for each hidden layers?
Tagged:
0
Best Answer
-
yyhuang Administrator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 364 RM Data ScientistHi @User36964,
The H2O deep learning can only define activate once for all hidden layers. If you want to add layer by layer and define the activation individually, please check out the deep learning extension or keras extension from marketplace.
https://marketplace.rapidminer.com/UpdateServer/faces/product_details.xhtml?productId=rmx_deeplearning
https://marketplace.rapidminer.com/UpdateServer/faces/product_details.xhtml?productId=rmx_keras
You can use different activation function when you add core layer, fully connected layer, convolution layer, embedding layer, etc..
Best,
YY7