Github user avulanov commented on the pull request:
https://github.com/apache/spark/pull/1290#issuecomment-63371703
@jkbradley (a) I found few papers with timing results, however with it was
with SVM. Moreover, the results differ from minutes to hours. Could you suggest
a paper with performance results of ANN on mnist8m? (b) I can compare against
single threaded C++ implementation. I think it will be much faster. Probably
the size of data is not enough to run it in distributed mode. Probably, we need
some dataset that cannot be used on a single machine. (c) Do you mean comparing
with other machine learners in Spark MLlib? To the best of my knowledge, there
is only one multiclass machine learner in MLlib, it is Bayesian. It is no
supposed to work with negative features.
---
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]
