[jira] [Commented] (MADLIB-1134) Neural Networks - MLP - Phase 2

[ASF GitHub Bot (JIRA)]

[ 
https://issues.apache.org/jira/browse/MADLIB-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16126051#comment-16126051
 ] 

ASF GitHub Bot commented on MADLIB-1134:


Github user asfgit closed the pull request at:

https://github.com/apache/incubator-madlib/pull/162


> Neural Networks - MLP - Phase 2
> ---
>
> Key: MADLIB-1134
> URL: https://issues.apache.org/jira/browse/MADLIB-1134
> Project: Apache MADlib
>  Issue Type: Improvement
>  Components: Module: Neural Networks
>Reporter: Frank McQuillan
>Assignee: Cooper Sloan
> Fix For: v1.12
>
>
> Follow on from https://issues.apache.org/jira/browse/MADLIB-413
> Story
> As a MADlib developer, I want to get 2nd phase implementation of NN going 
> with training and prediction functions, so that I can use this to build to an 
> MVP version for GA.
> Features to add:
> * weights for inputs
> * logic for n_tries
> * normalize inputs
> * L2 regularization
> * learning rate policy
> * warm start



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

[jira] [Commented] (MADLIB-1134) Neural Networks - MLP - Phase 2

[Cooper Sloan (JIRA)]

[ 
https://issues.apache.org/jira/browse/MADLIB-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16120655#comment-16120655
 ] 

Cooper Sloan commented on MADLIB-1134:
--

Very good article on regularization for NN:

https://piazza-resources.s3.amazonaws.com/ieytirtomz425i/ifyrgs0anxs3d5/Oct19Lecture.pdf?AWSAccessKeyId=AKIAIEDNRLJ4AZKBW6HA=1502245062=6FGb4J8zhez0uQWsu4xtefaKlFU%3D

> Neural Networks - MLP - Phase 2
> ---
>
> Key: MADLIB-1134
> URL: https://issues.apache.org/jira/browse/MADLIB-1134
> Project: Apache MADlib
>  Issue Type: Improvement
>  Components: Module: Neural Networks
>Reporter: Frank McQuillan
>Assignee: Cooper Sloan
> Fix For: v1.12
>
>
> Follow on from https://issues.apache.org/jira/browse/MADLIB-413
> Story
> As a MADlib developer, I want to get 2nd phase implementation of NN going 
> with training and prediction functions, so that I can use this to build to an 
> MVP version for GA.
> Features to add:
> * weights for inputs
> * logic for n_tries
> * normalize inputs
> * L2 regularization
> * learning rate policy
> * warm start



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

[jira] [Commented] (MADLIB-1134) Neural Networks - MLP - Phase 2

[ASF GitHub Bot (JIRA)]

[ 
https://issues.apache.org/jira/browse/MADLIB-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16116970#comment-16116970
 ] 

ASF GitHub Bot commented on MADLIB-1134:


GitHub user cooper-sloan opened a pull request:

https://github.com/apache/incubator-madlib/pull/162

MLP: Multilayer Perceptron Phase 2

JIRA: MADLIB-1134

Weights, warm start, n_tries,
regularization, learning rate policy,
standardization and tests.

You can merge this pull request into a Git repository by running:

$ git pull https://github.com/cooper-sloan/incubator-madlib mlp_phase2

Alternatively you can review and apply these changes as the patch at:

https://github.com/apache/incubator-madlib/pull/162.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 #162


commit 0d008d9995b1ffb5b35271318b878b396375456a
Author: Cooper Sloan 
Date:   2017-06-17T00:41:07Z

MLP: Multilayer Perceptron Phase 2

JIRA: MADLIB-1134

Weights, warm start, n_tries,
regularization, learning rate policy,
standardization and tests.




> Neural Networks - MLP - Phase 2
> ---
>
> Key: MADLIB-1134
> URL: https://issues.apache.org/jira/browse/MADLIB-1134
> Project: Apache MADlib
>  Issue Type: Improvement
>  Components: Module: Neural Networks
>Reporter: Frank McQuillan
>Assignee: Cooper Sloan
> Fix For: v1.12
>
>
> Follow on from https://issues.apache.org/jira/browse/MADLIB-413
> Story
> As a MADlib developer, I want to get 2nd phase implementation of NN going 
> with training and prediction functions, so that I can use this to build to an 
> MVP version for GA.
> Features to add:
> * weights for inputs
> * logic for n_tries
> * normalize inputs
> * L2 regularization
> * learning rate policy
> * warm start



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

[jira] [Commented] (MADLIB-1134) Neural Networks - MLP - Phase 2

[Frank McQuillan (JIRA)]

[ 
https://issues.apache.org/jira/browse/MADLIB-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16105853#comment-16105853
 ] 

Frank McQuillan commented on MADLIB-1134:
-

That looks like a good model to check against.

> Neural Networks - MLP - Phase 2
> ---
>
> Key: MADLIB-1134
> URL: https://issues.apache.org/jira/browse/MADLIB-1134
> Project: Apache MADlib
>  Issue Type: Improvement
>  Components: Module: Neural Networks
>Reporter: Frank McQuillan
>Assignee: Cooper Sloan
> Fix For: v1.12
>
>
> Follow on from https://issues.apache.org/jira/browse/MADLIB-413
> Story
> As a MADlib developer, I want to get 2nd phase implementation of NN going 
> with training and prediction functions, so that I can use this to build to an 
> MVP version for GA.
> Features to add:
> * weights for inputs
> * logic for n_tries
> * normalize inputs
> * L2 regularization
> * learning rate policy
> * warm start



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

[jira] [Commented] (MADLIB-1134) Neural Networks - MLP - Phase 2

[Cooper Sloan (JIRA)]

[ 
https://issues.apache.org/jira/browse/MADLIB-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16105769#comment-16105769
 ] 

Cooper Sloan commented on MADLIB-1134:
--

Let's do something like 
[this](https://issues.apache.org/jira/browse/MADLIB-1134) for ensuring 
correctness of our backprop.

> Neural Networks - MLP - Phase 2
> ---
>
> Key: MADLIB-1134
> URL: https://issues.apache.org/jira/browse/MADLIB-1134
> Project: Apache MADlib
>  Issue Type: Improvement
>  Components: Module: Neural Networks
>Reporter: Frank McQuillan
>Assignee: Cooper Sloan
> Fix For: v1.12
>
>
> Follow on from https://issues.apache.org/jira/browse/MADLIB-413
> Story
> As a MADlib developer, I want to get 2nd phase implementation of NN going 
> with training and prediction functions, so that I can use this to build to an 
> MVP version for GA.
> Features to add:
> * weights for inputs
> * logic for n_tries
> * normalize inputs
> * L2 regularization
> * learning rate policy
> * warm start



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

[jira] [Commented] (MADLIB-1134) Neural Networks - MLP - Phase 2

[Frank McQuillan (JIRA)]

[ 
https://issues.apache.org/jira/browse/MADLIB-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16103919#comment-16103919
 ] 

Frank McQuillan commented on MADLIB-1134:
-

If we don't support grouping in phase 2 but leave it in the interface, please 
make it clear in the user docs that it is not supported yet and will come later.

> Neural Networks - MLP - Phase 2
> ---
>
> Key: MADLIB-1134
> URL: https://issues.apache.org/jira/browse/MADLIB-1134
> Project: Apache MADlib
>  Issue Type: Improvement
>  Components: Module: Neural Networks
>Reporter: Frank McQuillan
>Assignee: Cooper Sloan
> Fix For: v1.12
>
>
> Follow on from https://issues.apache.org/jira/browse/MADLIB-413
> Story
> As a MADlib developer, I want to get 2nd phase implementation of NN going 
> with training and prediction functions, so that I can use this to build to an 
> MVP version for GA.
> Features to add:
> * weights for inputs
> * logic for n_tries
> * normalize inputs
> * L2 regularization
> * learning rate policy
> * warm start



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)