Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/9229#discussion_r54613493
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifierSuite.scala
---
@@ -49,7 +49,48 @@ class MultilayerPerceptronClassifierSuite extends
SparkFunSuite with MLlibTestSp
}
}
- // TODO: implement a more rigorous test
+ test("Test set weights by training restart") {
--- End diff --
I don't quite understand this unit test. It seems that the difference is
whether we want to keep using the same random number generator or reset the
seed to `12L` every 10 iterations. The solution could converge to a bad local
minimal but restarting doesn't always guarantee to fix it.
The content of the test doesn't match the test name. If we want to test
setting initial weights, we can show that with proper warm starts, the
algorithm converges faster in the same number of iterations.
---
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]
