GitHub user bgreeven opened a pull request:
https://github.com/apache/spark/pull/1290
[spark-2352] Implementation of an 1-hidden layer Artificial Neural Network
(ANN)
The code contains a single layer ANN, with variable number of inputs,
outputs and hidden nodes. It takes as input an RDD vector pairs, corresponding
to the training set with inputs and outputs.
A test program is also included, which also contains a graphical
representation that can be switched on using the "graph" parameter. Without it,
the summed squared error over the testing set is displayed.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/bgreeven/spark master
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/1290.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #1290
----
commit e60d8786d16e55264a61d8afc8d67bf06068aaaf
Author: Bert Greevenbosch <[email protected]>
Date: 2014-07-03T03:33:22Z
Create ParallelANN.scala
This is the main ParallelANN class and associated Model
commit 52da23d54254b38eea7181872e4caa25981c028e
Author: Bert Greevenbosch <[email protected]>
Date: 2014-07-03T03:34:41Z
Create GeneralizedSteepestDescendAlgorithm
This is the general steepest descend model, with as inputs Vectors and
outputs Vectors or Doubles.
commit 152b8baf84742ecd0c622d41d3804eb74c0310a3
Author: Bert Greevenbosch <[email protected]>
Date: 2014-07-03T03:36:31Z
Create TestParallelANN.scala
This is a test program for parallel ANNs.
commit c8af840149ac8d1903afe4ac826a626d030bd385
Author: Bert Greevenbosch <[email protected]>
Date: 2014-07-03T03:42:29Z
Create TestParallelANNgraphics.scala
Visualisation tools; only used when "TestParallelANN" is given the "graph"
parameter.
----
---
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.
---
