[
https://issues.apache.org/jira/browse/SPARK-2262?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
李力 updated SPARK-2262:
----------------------
Attachment: sat.trn.nol
sat.tst.nol
sparkELM.scala
The demo Spark codes of basic ELM (with randomly generated hidden nodes,
random neurons) are available for Classification and Regression , These random
hidden nodes include sigmoid .
The following sample of satimage is provided for you to try , Train
files and testing files are text files, each raw consisting of information of
one instance. First column are the expected output (target) for regression and
classification applications, the rest columns consist of different attributes
information of each instance.
author: lili
e-mail: [email protected]
company: Xi`an University of Posts & Telecommunications
> Extreme Learning Machines (ELM) for MLLib
> -----------------------------------------
>
> Key: SPARK-2262
> URL: https://issues.apache.org/jira/browse/SPARK-2262
> Project: Spark
> Issue Type: New Feature
> Components: MLlib
> Reporter: Erik Erlandson
> Assignee: Erik Erlandson
> Labels: features
> Attachments: sat.trn.nol, sat.tst.nol, sparkELM.scala
>
>
> MLLib has a gap in the NN space. There's some good reason for this, as
> batching gradient updates in traditional backprop training is known to not
> perform well.
> However, Extreme Learning Machines(ELM) combine support for nonlinear
> activation functions in a hidden layer with a batch-friendly linear training.
> There is also a body of ELM literature on various avenues for extension,
> including multi-category classification, multiple hidden layers and adaptive
> addition/deletion of hidden nodes.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
