Return-Path: Delivered-To: apmail-lucene-mahout-commits-archive@minotaur.apache.org Received: (qmail 33892 invoked from network); 7 May 2009 22:56:35 -0000 Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.3) by minotaur.apache.org with SMTP; 7 May 2009 22:56:35 -0000 Received: (qmail 67446 invoked by uid 500); 7 May 2009 22:56:35 -0000 Delivered-To: apmail-lucene-mahout-commits-archive@lucene.apache.org Received: (qmail 67367 invoked by uid 500); 7 May 2009 22:56:34 -0000 Mailing-List: contact mahout-commits-help@lucene.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: mahout-dev@lucene.apache.org Delivered-To: mailing list mahout-commits@lucene.apache.org Received: (qmail 67358 invoked by uid 99); 7 May 2009 22:56:34 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 07 May 2009 22:56:34 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=10.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.140] (HELO brutus.apache.org) (140.211.11.140) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 07 May 2009 22:56:24 +0000 Received: from brutus (localhost [127.0.0.1]) by brutus.apache.org (Postfix) with ESMTP id EEDE7234C044 for ; Thu, 7 May 2009 15:56:00 -0700 (PDT) Message-ID: <1782369950.1241736960977.JavaMail.www-data@brutus> Date: Thu, 7 May 2009 15:56:00 -0700 (PDT) From: confluence@apache.org To: mahout-commits@lucene.apache.org Subject: [CONF] Apache Lucene Mahout: Neural Network (page edited) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Virus-Checked: Checked by ClamAV on apache.org Neural Network (MAHOUT) edited by Ted Dunning Page: http://cwiki.apache.org/confluence/display/MAHOUT/Neural+Network Changes: http://cwiki.apache.org/confluence/pages/diffpagesbyversion.action?pageId=75593&originalVersion=2&revisedVersion=3 Content: --------------------------------------------------------------------- h1. Neural Networks Neural Networks are a means for classifying multi dimensional objects. We concentrate on implementing back propagation networks with one hidden layer as these networks have been covered by the [2006 NIPS map reduce paper|http://www.cs.stanford.edu/people/ang/papers/nips06-mapreducemulticore.pdf]. Those networks are capable of learning not only linear separating hyper planes but arbitrary decision boundaries. h2. Strategy for parallel backpropagation network h2. Design of implementation --------------------------------------------------------------------- CONFLUENCE INFORMATION This message is automatically generated by Confluence Unsubscribe or edit your notifications preferences http://cwiki.apache.org/confluence/users/viewnotifications.action If you think it was sent incorrectly contact one of the administrators http://cwiki.apache.org/confluence/administrators.action If you want more information on Confluence, or have a bug to report see http://www.atlassian.com/software/confluence