Github user elyast commented on the pull request:
https://github.com/apache/spark/pull/1290#issuecomment-54734035
Hi @avulanov I run your NeuralNetworkSuite (from your fork / neuralnetwork
brach), however it fails randomly, are you sure you have implemented in
correctly?
By the way guys did you thought about regularization?
@bgreeven I checked your though and I see a lots of iterations I would
recommend to replace it with breeze vector operations since it will be much
faster (its true also for matlab or R code).
Let me know what do you think and if I can help with anything.
Last thing to consider is to factor out activation function, so instead
sigmoid one can use softmax, tan or else.
---
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
