Return-Path: X-Original-To: apmail-singa-dev-archive@minotaur.apache.org Delivered-To: apmail-singa-dev-archive@minotaur.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id B3CE3181D6 for ; Sun, 20 Sep 2015 12:37:15 +0000 (UTC) Received: (qmail 51862 invoked by uid 500); 20 Sep 2015 12:37:15 -0000 Delivered-To: apmail-singa-dev-archive@singa.apache.org Received: (qmail 51835 invoked by uid 500); 20 Sep 2015 12:37:15 -0000 Mailing-List: contact dev-help@singa.incubator.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@singa.incubator.apache.org Delivered-To: mailing list dev@singa.incubator.apache.org Received: (qmail 51825 invoked by uid 99); 20 Sep 2015 12:37:15 -0000 Received: from Unknown (HELO spamd4-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Sun, 20 Sep 2015 12:37:15 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd4-us-west.apache.org (ASF Mail Server at spamd4-us-west.apache.org) with ESMTP id 34851C098E for ; Sun, 20 Sep 2015 12:37:15 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd4-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: 1.795 X-Spam-Level: * X-Spam-Status: No, score=1.795 tagged_above=-999 required=6.31 tests=[KAM_ASCII_DIVIDERS=0.8, KAM_LAZY_DOMAIN_SECURITY=1, RP_MATCHES_RCVD=-0.006, URIBL_BLOCKED=0.001] autolearn=disabled Received: from mx1-us-east.apache.org ([10.40.0.8]) by localhost (spamd4-us-west.apache.org [10.40.0.11]) (amavisd-new, port 10024) with ESMTP id TxZp_fAkTZMQ for ; Sun, 20 Sep 2015 12:37:05 +0000 (UTC) Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by mx1-us-east.apache.org (ASF Mail Server at mx1-us-east.apache.org) with SMTP id 580E242B7B for ; Sun, 20 Sep 2015 12:37:05 +0000 (UTC) Received: (qmail 51643 invoked by uid 99); 20 Sep 2015 12:37:04 -0000 Received: from arcas.apache.org (HELO arcas.apache.org) (140.211.11.28) by apache.org (qpsmtpd/0.29) with ESMTP; Sun, 20 Sep 2015 12:37:04 +0000 Date: Sun, 20 Sep 2015 12:37:04 +0000 (UTC) From: "ASF subversion and git services (JIRA)" To: dev@singa.incubator.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Commented] (SINGA-10) Add Support for Recurrent Neural Networks (RNN) MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394 [ https://issues.apache.org/jira/browse/SINGA-10?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14899905#comment-14899905 ] ASF subversion and git services commented on SINGA-10: ------------------------------------------------------ Commit 79a241c8bb6c520979d52c895f4958c2b901cd47 in incubator-singa's branch refs/heads/master from wang sheng [ https://git-wip-us.apache.org/repos/asf?p=incubator-singa.git;h=79a241c ] SINGA-10 Add Support for Recurrent Neural Networks (RNN) improve extract_cluster function in tool.cc - we read the last occurrence of "cluster" - content are the first occurrence of "{" and "}" after "cluster" format rnnlm.h and common.cc > Add Support for Recurrent Neural Networks (RNN) > ----------------------------------------------- > > Key: SINGA-10 > URL: https://issues.apache.org/jira/browse/SINGA-10 > Project: Singa > Issue Type: New Feature > Reporter: wangwei > Assignee: Zheng Kaiping > > The training algorithm for RNNs is Back-Propagation through time (BPTT). It is similar to the BP algorithm for feed-forward neural networks. > The model structures are quite different to feed-forward models. Hence, we may need to inherit the base NeuralNet class to create a RNN class. The RNN class overrides the SetupNeurlNet function to: > 1. parse user configuration and create the RNN graph with (circles) > 2. broke the circles and expand it through time. > 3. create and setup layers > Model partitioning id not considered in this ticket. -- This message was sent by Atlassian JIRA (v6.3.4#6332)