Community & Support
Learn
Marketplace
Discussions
Categories
Discussions
General
Platform
Academic
Partner
Regional
User Groups
Documentation
Events
Altair Exchange
Share or Download Projects
Resources
News & Instructions
Programs
YouTube
Employee Resources
This tab can be seen by employees only. Please do not share these resources externally.
Groups
Join a User Group
Support
Altair RISE
A program to recognize and reward our most engaged community members
Nominate Yourself Now!
Home
Discussions
Community Q&A
Deep Learning Loss Function
Nienke
Hi,
I was wondering which loss function is selected in case the Deep Learning model is selected and the "Loss_Function" is set to "Automatic".
For most parameters this is specified in the documentation. However, for the loss function this is not explained in the documentation. (I can't add the link to the documentation page...)
Thanks in advance.
Nienke
Find more posts tagged with
AI Studio
Deep Learning + Neural Nets
Auto Model
Accepted answers
jacobcybulski
As this is the H2O.ai operator, the best is to look at their specs on the web site. Here is what they say on this (for some reason in their discussion of "distribution").
'By default, the loss function method performs AUTO distribution. In this case, the algorithm will guess the model type based on the response column type (specified using
y
). More specifically, if the response column type is numeric, AUTO defaults to “gaussian”; if categorical, AUTO defaults to bernoulli or multinomial depending on the number of response categories.'
Jacob
All comments
jacobcybulski
As this is the H2O.ai operator, the best is to look at their specs on the web site. Here is what they say on this (for some reason in their discussion of "distribution").
'By default, the loss function method performs AUTO distribution. In this case, the algorithm will guess the model type based on the response column type (specified using
y
). More specifically, if the response column type is numeric, AUTO defaults to “gaussian”; if categorical, AUTO defaults to bernoulli or multinomial depending on the number of response categories.'
Jacob
Quick Links
All Categories
Recent Discussions
Activity
Unanswered
日本語 (Japanese)
한국어(Korean)
Groups