Github user avulanov commented on the pull request:
https://github.com/apache/spark/pull/1290#issuecomment-102566723
@wangzk you are welcome!
Added Dropout
(http://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf)
implementation to the new version. It is implemented as a different type of
network topology. Example of use:
```
val inputDropoutProb = 0.5
val layerDropoutProb = 0.5
val topology = FeedForwardTopology.multiLayerPerceptron(Array[Int](780, 32,
10), true)
val dropoutTopology = new DropoutTopology(topology.layers,
inputDropoutProb,layerDropoutProb)
val trainer = new FeedForwardTrainer(dropoutTopology, 780,
10).setBatchSize(100)
trainer.LBFGSOptimizer.setConvergenceTol(1e-4).setNumIterations(100)
val model = new ANNClassifier(trainer).train(train)
```
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
