The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
Hidden Layer Activation Functions
University Professor
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, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 364 
RM Data Scientist
Hi @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
