Github user witgo commented on the pull request:
https://github.com/apache/spark/pull/3222#issuecomment-67109137
@avulanov
If the `MLP` contains multi-layer. Usually don't need to l2
regularization(see: [Dropout: A simple way to prevent neural networks from
overfitting](http://www.jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf)
).
eg:
```scala
val topology= Array(numVisible, 100, 10)
val model = MLP.runSGD(annData, topology, batchSize, maxIterations, 0.05,
0.0, 0.0, 0.5)
```
---
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
