Github user JeremyNixon commented on a diff in the pull request:
https://github.com/apache/spark/pull/13617#discussion_r69146687
--- Diff: mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala ---
@@ -438,6 +478,27 @@ private[ml] object FeedForwardTopology {
}
FeedForwardTopology(layers)
}
+
+ /**
+ * Creates a multi-layer perceptron for regression
+ *
+ * @param layerSizes sizes of layers including input and output size
--- End diff --
That's right @viirya, the output is almost always 1. There are important
corner cases with multiple outputs, like
[Overfeat's](http://arxiv.org/pdf/1312.6229v4.pdf) state of the art object
localization predictions (see section 4.2). Instead of training 1 linear
regression model on top of the network's generated features, it trains 4 linear
regression models that each predict the corner of a box that surrounds an
object in the image. I think that keeping the flexibility makes sense, but
we'll need to add
[SPARK-9120](https://issues.apache.org/jira/browse/SPARK-9120).
---
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]
