grh.mur.at - machine learning http://grh.mur.at/taxonomy/term/36/0 en New project: auphonic http://grh.mur.at/blog/new-project-auphonic <p> Currently I am working on the <a href="http://auphonic.com">auphonic project</a>, which involves machine learning, audio signal processing, web development, open-source technologies and much more. </p> <p> So don't expect many updates on my mur.at page, I will write about new things on the <a href="http://auphonic.com/blog">auphonic blog</a>. You can subscribe to the <a href="http://feeds.feedburner.com/auphonic-latest">auphonic feed</a> or follow <a href="http://twitter.com/auphonic">@auphonic</a> on twitter. </p> audio english blog machine learning numpy python Signal Processing web Wed, 06 Jul 2011 16:19:43 +0000 grh 252 at http://grh.mur.at Echo State Networks with Filter Neurons and a Delay&Sum Readout http://grh.mur.at/publications/esns-with-filters-and-delay-sum-readout <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Year:&nbsp;</div> 2010 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> <div class="field-item even"> <div class="field-label-inline"> Authors:&nbsp;</div> Helmut Hauser </div> </div> </div> <div class="field field-type-text field-field-pubtype"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Type:&nbsp;</div> Journal paper </div> </div> </div> <div class="field field-type-text field-field-publisher"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Publisher:&nbsp;</div> <p>Neural Networks</p> </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Abstract:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p>Echo state networks (ESNs) are a novel approach to recurrent neural network training with the advantage of a very simple and linear learning algorithm. It has been demonstrated that ESNs outperform other methods on a number of benchmark tasks. Although the approach is appealing, there are still some inherent limitations in the original formulation.</p> <p>Here we suggest two enhancements of this network model.<br /> First, the previously proposed idea of filters in neurons is extended to arbitrary infinite impulse response (IIR) filter neurons. This enables such networks to learn multiple attractors and signals at different timescales, which is especially important for modeling real-world time series.<br /> Second, a delay&amp;sum readout is introduced, which adds trainable delays in the synaptic connections of output neurons and therefore vastly improves the memory capacity of echo state networks.</p> <p>It is shown in commonly used benchmark tasks and real-world examples, that this new structure is able to significantly outperform standard ESNs and other state-of-the-art models for nonlinear dynamical system modeling.</p> </div> </div> </div> <div class="field field-type-filefield field-field-publication"> <div class="field-label">Publication:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-pdf"><img class="field-icon-application-pdf" alt="application/pdf icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-pdf.png" /></div><a href="http://grh.mur.at/sites/default/files/ESNFilterDelaySum_0.pdf" type="application/pdf; length=2375237" title="ESNFilterDelaySum.pdf">Echo State Networks with Filter Neurons and a Delay&amp;Sum Readout (preprint)</a></div> </div> </div> </div> echo state networks machine learning neural networks nonlinear reservoir computing Signal Processing Mon, 13 Jul 2009 17:05:14 +0000 grh 174 at http://grh.mur.at Reservoir Computing: a powerful Black-Box Framework for Nonlinear Audio Processing http://grh.mur.at/publications/reservoir-computing-for-audio <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Year:&nbsp;</div> 2009 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> </div> </div> <div class="field field-type-text field-field-pubtype"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Type:&nbsp;</div> Conference paper </div> </div> </div> <div class="field field-type-text field-field-publisher"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Publisher:&nbsp;</div> <p>Proc. of the 12th Int. Conference on Digital Audio Effects (DAFx-09)</p> </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Abstract:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p>This paper proposes reservoir computing as a general framework for nonlinear audio processing.<br /> Reservoir computing is a novel approach to recurrent neural network training with the advantage of a very simple and linear learning algorithm. It can in theory approximate arbitrary nonlinear dynamical systems with arbitrary precision, has an inherent temporal processing capability and is therefore well suited for many nonlinear audio processing problems. Always when nonlinear relationships are present in the data and time information is crucial, reservoir computing can be applied.</p> <p>Examples from three application areas are presented: nonlinear system identification of a tube amplifier emulator algorithm, nonlinear audio prediction, as necessary in a wireless transmission of audio where dropouts may occur, and automatic melody transcription out of a polyphonic audio stream, as one example from the big field of music information retrieval.<br /> Reservoir computing was able to outperform state-of-the-art alternative models in all studied tasks.</p> </div> </div> </div> <div class="field field-type-filefield field-field-publication"> <div class="field-label">Publication:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-pdf"><img class="field-icon-application-pdf" alt="application/pdf icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-pdf.png" /></div><a href="http://grh.mur.at/sites/default/files/RCandAudio.pdf" type="application/pdf; length=1947747" title="RCandAudio.pdf">Reservoir Computing DAFx-09 paper</a></div> </div> </div> </div> <div class="field field-type-filefield field-field-media"> <div class="field-label">Media:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-zip"><img class="field-icon-application-zip" alt="application/zip icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/package-x-generic.png" /></div><a href="http://grh.mur.at/sites/default/files/DAFX09AudioExamples.zip" type="application/zip; length=5518643" title="DAFX09AudioExamples.zip">Audio Examples for DAFx-09 paper (5.3 MB)</a></div> </div> </div> </div> audio echo state networks machine learning neural networks nonlinear reservoir computing Signal Processing Thu, 25 Jun 2009 14:23:28 +0000 grh 154 at http://grh.mur.at Master Thesis on Echo State Networks http://grh.mur.at/publications/master-thesis-echo-state-networks <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Year:&nbsp;</div> 2008 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> </div> </div> <div class="field field-type-text field-field-pubtype"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Type:&nbsp;</div> Master Thesis </div> </div> </div> <div class="field field-type-text field-field-publisher"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Publisher:&nbsp;</div> <p>Institute for Theoretical Computer Science, TU Graz, Austria</p> </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Abstract:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p><strong> Echo State Networks with Filter Neurons and a Delay&amp;Sum Readout with Applications in Audio Signal Processing </strong></p> <p>Echo state networks (ESNs) are a novel approach to recurrent neural network training with the advantage of a very simple and linear learning algorithm. They can in theory approximate arbitrary nonlinear dynamical system with arbitrary precision (universal approximation property), have an inherent temporal processing capability, and are therefore a very powerful enhancement of linear blackbox modeling techniques in nonlinear domain. It was demonstrated on a number of benchmark tasks, that echo state networks outperform other methods for nonlinear dynamical modeling.</p> <p>This thesis suggests two enhancements of the original network model. First, the previously proposed idea of filters in neurons is extended to arbitrary infinite impulse response (IIR) filter neurons and the ability of such networks to learn multiple attractors is demonstrated. Second, a delay&amp;sum readout is introduced, which adds trainable delays in the synaptic connections of output neurons and therefore vastly improves the memory capacity of echo state networks. It is shown in benchmark tasks that this new structure is able to outperform standard ESNs and other models, moreover no other comparable method for sparse nonlinear system identification with long-term dependencies could be found in literature.</p> <p>Finally real-world applications in the context of audio signal processing are presented and compared to state-of-the-art alternative methods. The first example is a nonlinear system identification task of a tube amplifier and afterwards ESNs are trained for nonlinear audio prediction, as necessary in audio restoration or in the wireless transmission of audio where dropouts may occur. Furthermore an efficient and open source C++ library for echo state networks was developed and is briefly presented.</p> <p>The audio examples can be downloaded below.</p> </div> </div> </div> <div class="field field-type-filefield field-field-publication"> <div class="field-label">Publication:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-pdf"><img class="field-icon-application-pdf" alt="application/pdf icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-pdf.png" /></div><a href="http://grh.mur.at/sites/default/files/MasterThesis.pdf" type="application/pdf; length=5455508" title="MasterThesis.pdf">Master Thesis</a></div> </div> </div> </div> <div class="field field-type-filefield field-field-media"> <div class="field-label">Media:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-zip"><img class="field-icon-application-zip" alt="application/zip icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/package-x-generic.png" /></div><a href="http://grh.mur.at/sites/default/files/ThesisAudioExamples.zip" type="application/zip; length=6321813" title="ThesisAudioExamples.zip">Thesis Audio Examples (6 MB)</a></div> </div> </div> </div> audio echo state networks machine learning neural networks Signal Processing Wed, 24 Jun 2009 19:01:53 +0000 grh 150 at http://grh.mur.at Echo State Networks in Audio Processing http://grh.mur.at/publications/echo-state-networks-audio-processing <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Year:&nbsp;</div> 2007 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> </div> </div> <div class="field field-type-text field-field-pubtype"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Type:&nbsp;</div> Technical report </div> </div> </div> <div class="field field-type-text field-field-publisher"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Publisher:&nbsp;</div> <p>Internet Publication</p> </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Abstract:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p>In this article echo state networks, a special form of recurrent neural networks, are discussed in the area of nonlinear audio signal processing. Echo state networks are a novel approach in recurrent neural networks with a very easy (linear) training algorithm.<br /> Signal processing examples in nonlinear system identification (valve distortion, clipping), inverse modeling (quality enhancement) and audio prediction are briefly presented and discussed.</p> </div> </div> </div> <div class="field field-type-filefield field-field-publication"> <div class="field-label">Publication:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-pdf"><img class="field-icon-application-pdf" alt="application/pdf icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-pdf.png" /></div><a href="http://grh.mur.at/sites/default/files/ESNinAudioProcessing.pdf" type="application/pdf; length=1231516" title="ESNinAudioProcessing.pdf">ESNs in Audio Processing</a></div> </div> </div> </div> audio machine learning neural networks reservoir computing Signal Processing Wed, 24 Jun 2009 18:34:50 +0000 grh 148 at http://grh.mur.at Genetische Algorithmen in Komposition und Computermusik http://grh.mur.at/publications/genetische-algorithmen-komposition-und-computermusik <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Year:&nbsp;</div> 2003 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> </div> </div> <div class="field field-type-text field-field-pubtype"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Type:&nbsp;</div> Technical report </div> </div> </div> <div class="field field-type-text field-field-publisher"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Publisher:&nbsp;</div> <p>Internet Publication</p> </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Abstract:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p>Meist werden komplexe Systeme von Algorithmen in der algorithmischen Komposition<br /> verwendet. Dadurch entsteht eine Vielfalt an Parameter, die die intuitive Steuerung solcher<br /> Systeme erschweren.<br /> Mit Hilfe von Interaktiven Genetischen Algorithmen (IGA) kann man Variationen dieser<br /> unzähligen Parameter nach eigenen ästhetischen Vorstellungen „züchten“, ohne ein Wissen<br /> über die darunter liegende Struktur haben zu müssen und hat trotzdem noch ein hohes Maß an<br /> Kontrolle.<br /> Diese Arbeit bietet einen Überblick von Anwendungen Genetischer Algorithmen in der Musik und präsentiert eine neue Implementation.</p> </div> </div> </div> <div class="field field-type-filefield field-field-publication"> <div class="field-label">Publication:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-pdf"><img class="field-icon-application-pdf" alt="application/pdf icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-pdf.png" /></div><a href="http://grh.mur.at/sites/default/files/GAinKomposition.pdf" type="application/pdf; length=617598" title="GAinKomposition.pdf">Genetische Algorithmen in Komposition und Computermusik</a></div> </div> </div> </div> machine learning Pd Wed, 24 Jun 2009 18:10:35 +0000 grh 144 at http://grh.mur.at aureservoir http://grh.mur.at/software/aureservoir.html <div class="field field-type-text field-field-description"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Short Description:&nbsp;</div> <p>C++ library with python bindings for reservoir computing neural networks (echo state networks)</p> </div> </div> </div> <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Started in:&nbsp;</div> 2007 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> </div> </div> <div class="field field-type-text field-field-license"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> License:&nbsp;</div> GNU Library or "Lesser" General Public License (LGPL) </div> </div> </div> <div class="field field-type-text field-field-progamming-lang"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Programming language:&nbsp;</div> C++, Python </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Overview:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p> Reservoir computing is a recent kind of recurrent neural network computation, where only the output weights are trained. This has the big advantage that training is a simple linear regression task and one cannot get into a local minimum. Such a network consists of a randomly created, fixed, sparse recurrent reservoir and a trainable output layer connected to this reservoir. Most known types are the "Echo State Network" and the "Liquid State Machine", which achieved very promising results on various machine learning benchmarks. </p> <p> This library should be an open source (L-GPL) and very efficient implementation of Echo State Networks with bindings to scientific computation packages (so far to <a href="http://www.scipy.org/">python/numpy</a>, <a href="http://www.puredata.info/">Pure Data</a> and <a href="http://www.octave.org/">octave</a> are in work, everyone is invited to make a Matlab binding) for offline and realtime simulations. It can be extended in an easy way with new simulation, training and adaptation algorithms, which are function objects and automatically used by the main classes. </p> <p> For a theoretical overview and some papers about Echo State Networks see: <a href="http://www.scholarpedia.org/article/Echo_State_Network">Echo State Networks</a> and for a detailed description, examples, documentation, downloads and installation instructions please visit the project page. </p> </div> </div> </div> <div class="field field-type-link field-field-software-url"> <div class="field-label">Project page URL:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <a href="http://aureservoir.sourceforge.net/">aureservoir project page</a> </div> <div class="field-item even"> <a href="http://sourceforge.net/projects/aureservoir/">aureservoir sourceforge page</a> </div> <div class="field-item odd"> <a href="https://lists.sourceforge.net/lists/listinfo/aureservoir-user">aureservoir mailing list</a> </div> </div> </div> <div class="field field-type-link field-field-version-url"> <div class="field-label">Version Control System URL:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <a href="https://aureservoir.svn.sourceforge.net/svnroot/aureservoir/">aureservoir SVN repository</a> </div> </div> </div> machine learning neural networks python Wed, 24 Jun 2009 15:46:39 +0000 grh 143 at http://grh.mur.at TheBrain http://grh.mur.at/software/thebrain.html <div class="field field-type-text field-field-description"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Short Description:&nbsp;</div> <p>TheBrain is a small C++ library for artificial neural nets</p> </div> </div> </div> <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Started in:&nbsp;</div> 2005 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> </div> </div> <div class="field field-type-text field-field-license"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> License:&nbsp;</div> GNU General Public License (GPL) </div> </div> </div> <div class="field field-type-text field-field-progamming-lang"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Programming language:&nbsp;</div> C++ </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Overview:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p>TheBrain is a small C++ library for artificial neural networks.<br /> Currently I implemented a feedforward, a recurrent neural net and wrappers for <a href="http://gem.iem.at">GEM</a>, which calculate audio signals out of video frames.</p> <p>TheBrain consists of the following 2 objects:<br /> <em>pix_linNN</em> (with a linear feedforward neural net) and <em>pix_recNN</em> (with a recurrent neural net).</p> <p><em>pix_recNN</em>/<em>pix_linNN</em> are thought as an instument/interface.<br /> This instrument should be useful as a general experimental video interface to generate audio. You can train an artificial neural net with playing audio samples to specific video frames in real-time - so you are able to produce specific sounds to specific video frames and you can control the sound with making some movements, colors, ... (whatever) in front of the camera.<br /> The main interest for me was not to train the net exactly to reproduce these samples, but to make experimental sounds, which are "between" all the trained samples.</p> <p><em>pix_linNN</em> has one neuron per audio sample: this neuron has three inputs (a RGB-signal), a weight vector for each of the inputs, a bias value and a linear output function.</p> <p><em>pix_recNN</em> uses a 2 layer recurrent neural net (which is much better for time-based information like video/music). </p> </div> </div> </div> <div class="field field-type-link field-field-version-url"> <div class="field-label">Version Control System URL:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <a href="http://pure-data.svn.sourceforge.net/viewvc/pure-data/trunk/externals/grh">SVN repository of pix_linNN and pix_recNN</a> </div> </div> </div> <div class="field field-type-filefield field-field-tarball"> <div class="field-label">Release Tarball:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-octet-stream"><img class="field-icon-application-octet-stream" alt="application/octet-stream icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-octet-stream.png" /></div><a href="http://grh.mur.at/sites/default/files/pix_linNN.tar_.gz" type="application/octet-stream; length=15270" title="pix_linNN.tar_.gz">pix_linNN source tarball</a></div> </div> <div class="field-item even"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-octet-stream"><img class="field-icon-application-octet-stream" alt="application/octet-stream icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-octet-stream.png" /></div><a href="http://grh.mur.at/sites/default/files/pix_recNN.tar__0.gz" type="application/octet-stream; length=19868" title="pix_recNN.tar_.gz">pix_recNN source tarball</a></div> </div> </div> </div> <div class="field field-type-filefield field-field-binary"> <div class="field-label">Release Binary:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-octet-stream"><img class="field-icon-application-octet-stream" alt="application/octet-stream icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-octet-stream.png" /></div><a href="http://grh.mur.at/sites/default/files/pix_linNN.pd_linux" type="application/octet-stream; length=37912" title="pix_linNN.pd_linux">pix_linNN binary for linux</a></div> </div> <div class="field-item even"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-octet-stream"><img class="field-icon-application-octet-stream" alt="application/octet-stream icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-octet-stream.png" /></div><a href="http://grh.mur.at/sites/default/files/pix_recNN.pd_linux" type="application/octet-stream; length=41320" title="pix_recNN.pd_linux">pix_recNN binary for linux</a></div> </div> </div> </div> machine learning neural networks Pd Wed, 24 Jun 2009 12:38:57 +0000 grh 130 at http://grh.mur.at GApop http://grh.mur.at/software/gapop.html <div class="field field-type-text field-field-description"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Short Description:&nbsp;</div> <p>a genetic algorithm external for Pd and MAX/MSP</p> </div> </div> </div> <div class="field field-type-number-integer field-field-year"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Started in:&nbsp;</div> 2004 </div> </div> </div> <div class="field field-type-text field-field-authors"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Authors:&nbsp;</div> Georg Holzmann </div> </div> </div> <div class="field field-type-text field-field-license"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> License:&nbsp;</div> GNU General Public License (GPL) </div> </div> </div> <div class="field field-type-text field-field-progamming-lang"> <div class="field-items"> <div class="field-item odd"> <div class="field-label-inline-first"> Programming language:&nbsp;</div> C++ </div> </div> </div> <div class="field field-type-text field-field-abstract"> <div class="field-label">Overview:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <p>GApop is a genetic algorithm external for <a href="http://puredata.info">Pure Data</a> and MAX/MSP, using the <a href="http://puredata.info/Members/thomas/flext">flext-layer</a> by Thomas Grill.</p> </div> </div> </div> <div class="field field-type-link field-field-version-url"> <div class="field-label">Version Control System URL:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <a href="http://pure-data.svn.sourceforge.net/viewvc/pure-data/trunk/externals/grh/GApop/">GApop SVN repository</a> </div> </div> </div> <div class="field field-type-filefield field-field-tarball"> <div class="field-label">Release Tarball:&nbsp;</div> <div class="field-items"> <div class="field-item odd"> <div class="filefield-file clear-block"><div class="filefield-icon field-icon-application-octet-stream"><img class="field-icon-application-octet-stream" alt="application/octet-stream icon" src="http://grh.mur.at/sites/all/modules/filefield/icons/protocons/16x16/mimetypes/application-octet-stream.png" /></div><a href="http://grh.mur.at/sites/default/files/GApop0.1.tar_.gz" type="application/octet-stream; length=17115" title="GApop0.1.tar_.gz">GApop 0.1 source tarball</a></div> </div> </div> </div> flext machine learning Pd Wed, 24 Jun 2009 12:29:01 +0000 grh 129 at http://grh.mur.at