[jira] [Resolved] (MADLIB-958) Non-linear SVM - gaussian kernel in-mem

["Frank McQuillan (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/MADLIB-958?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Frank McQuillan resolved MADLIB-958.
------------------------------------
    Resolution: Fixed

> Non-linear SVM - gaussian kernel in-mem
> ---------------------------------------
>
>                 Key: MADLIB-958
>                 URL: https://issues.apache.org/jira/browse/MADLIB-958
>             Project: Apache MADlib
>          Issue Type: New Feature
>          Components: Module: Support Vector Machines
>            Reporter: Frank McQuillan
>            Assignee: Xiaocheng Tang
>             Fix For: v1.9
>
>
> Story
> As a MADlib developer, I want to implement a Gaussian kernel for the SVM algorithm in-memory, for smaller numbers of features:
> This is a follow on to:
> https://issues.apache.org/jira/browse/MADLIB-937
> Logic:
> IF (smaller number of features)
>   Use https://issues.apache.org/jira/browse/MADLIB-958 (i.e., this story)
> ELSE 
>   Use https://issues.apache.org/jira/browse/MADLIB-937
> This approach allows us to support large numbers of features not constrained by the PostgreSQL 1 GB internal agg limit.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)