Github user Zehao commented on the pull request:
https://github.com/apache/spark/pull/1290#issuecomment-81390078
Hi, are you still working on this PR? I have a few questions about the
latest code from https://github.com/bgreeven/spark .
1. I ran the code and found that the parameter `gradient` in
`ANNUpdater.compute` were all zeros during each iteration , and so it didn't
change the weights. Does it matter ? I haven't well understand the difference
between `ANNLeastSquaresGradient.compute` and `ANNUpdater.compute` yet , but
`ANNLeastSquaresGradient.compute` do change the weights.
2. In the model , every neuron has a bias node , is it the standard ANN
model?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
