<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href="http://www.blogger.com/styles/atom.css" type="text/css"?><feed xmlns='http://www.w3.org/2005/Atom' xmlns:openSearch='http://a9.com/-/spec/opensearchrss/1.0/' xmlns:georss='http://www.georss.org/georss' xmlns:gd='http://schemas.google.com/g/2005' xmlns:thr='http://purl.org/syndication/thread/1.0'><id>tag:blogger.com,1999:blog-10230918</id><updated>2011-07-28T22:24:17.995-07:00</updated><title type='text'>[Booby-Funkybeat-hugo]'s cahier de brouillons</title><subtitle type='html'>Voici le nouveau support d'écriture de funkybeat qui lui permet de stocker les adresses des pages qu'il a lues, devrait, fait semblant d'avoir lues...</subtitle><link rel='http://schemas.google.com/g/2005#feed' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/posts/default'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default?max-results=100'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/'/><link rel='hub' href='http://pubsubhubbub.appspot.com/'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><generator version='7.00' uri='http://www.blogger.com'>Blogger</generator><openSearch:totalResults>17</openSearch:totalResults><openSearch:startIndex>1</openSearch:startIndex><openSearch:itemsPerPage>100</openSearch:itemsPerPage><entry><id>tag:blogger.com,1999:blog-10230918.post-5612690539677055466</id><published>2010-08-30T06:55:00.000-07:00</published><updated>2010-08-30T07:03:45.519-07:00</updated><title type='text'>Strategies for online inference of model-based clustering in large and growing networks</title><content type='html'>In this paper we adapt online estimation strategies to perform model-based clustering on large networks. Our work focuses on two algorithms, the first based on the SAEM algorithm, and the second on variational methods. These two strategies are compared with existing approaches on simulated and real data.  We use the method to decipher the connexion structure of the political websphere during the U.S. political campaign in 2008. We show that our online EM-based algorithms offer a good trade-off between precision and speed, when estimating parameters for mixture distributions in the context of random graphs.&lt;br /&gt;&lt;br /&gt;Paper is published in &lt;a href="http://projecteuclid.org/DPubS?service=UI&amp;amp;version=1.0&amp;amp;verb=Display&amp;amp;handle=euclid.aoas/1280842136"&gt;AOAS&lt;/a&gt; and the pdf is available  &lt;a href="http://pbil.univ-lyon1.fr/members/fpicard/franckpicard_fichiers/pdf/ZPM10.pdf"&gt;here&lt;/a&gt;.&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-5612690539677055466?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/5612690539677055466/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=5612690539677055466' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/5612690539677055466'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/5612690539677055466'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2010/08/strategies-for-online-inference-of.html' title='Strategies for online inference of model-based clustering in large and growing networks'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-31424672767440813</id><published>2010-03-16T04:32:00.000-07:00</published><updated>2010-03-16T04:41:22.783-07:00</updated><title type='text'>Clustering based on random graph model embedding vertex features</title><content type='html'>Large datasets with interactions between objects are common to numerous scientific fields including the social sciences and biology, as well as being a feature of specific phenomena such as the internet. The interactions naturally define a graph, and a common way of exploring and summarizing such datasets is graph clustering. Most techniques for clustering graph vertices use only the topology of connections, while ignoring information about the vertices’ features. In this paper we provide a clustering algorithm that harnesses both types of data, based on a statistical model with a latent structure characterizing each vertex both by a vector of features and by its connectivity. We perform simulations to compare our algorithm with existing approaches, and also evaluate our method using real datasets based on hypertext documents. We find that our algorithm successfully exploits whatever information is found both in the connectivity pattern and in the features.&lt;br /&gt;&lt;br /&gt;The future of &lt;a href="http://demos.labs.exalead.com/constellations/?q=constellations+exalead&amp;amp;l=all"&gt;Constellations&lt;/a&gt; ? Read the paper &lt;a href="http://dx.doi.org/10.1016/j.patrec.2010.01.026"&gt;here&lt;/a&gt; or be crafty ;-)&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-31424672767440813?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/31424672767440813/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=31424672767440813' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/31424672767440813'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/31424672767440813'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2010/03/clustering-based-on-random-graph-model.html' title='Clustering based on random graph model embedding vertex features'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-4980977316771836424</id><published>2009-06-06T13:49:00.000-07:00</published><updated>2009-06-07T04:58:49.239-07:00</updated><title type='text'>Oh my God, it's full of stars !!</title><content type='html'>To get a closer idea of the MixNet algorithm behavior applied on hypertext documents, just take a look at the Exalead application  "&lt;a href="http://constellations.labs.exalead.com/?q=funkybeat&amp;amp;l=fr"&gt;Constellations&lt;/a&gt;".&lt;br /&gt;&lt;br /&gt;&lt;a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://2.bp.blogspot.com/__knvamoEAiA/SiurQvGKFOI/AAAAAAAAAO8/wHfpIn8oHBY/s1600-h/Image+2.png"&gt;&lt;img style="display:block; margin:0px auto 10px; text-align:center;cursor:pointer; cursor:hand;width: 320px; height: 182px;" src="http://2.bp.blogspot.com/__knvamoEAiA/SiurQvGKFOI/AAAAAAAAAO8/wHfpIn8oHBY/s320/Image+2.png" border="0" alt="" id="BLOGGER_PHOTO_ID_5344553686813775074" /&gt;&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;Enjoy !&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-4980977316771836424?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/4980977316771836424/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=4980977316771836424' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/4980977316771836424'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/4980977316771836424'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2009/06/oh-my-god-its-full-of-stars.html' title='Oh my God, it&apos;s full of stars !!'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><media:thumbnail xmlns:media='http://search.yahoo.com/mrss/' url='http://2.bp.blogspot.com/__knvamoEAiA/SiurQvGKFOI/AAAAAAAAAO8/wHfpIn8oHBY/s72-c/Image+2.png' height='72' width='72'/><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-7021162606567818209</id><published>2008-09-15T02:39:00.000-07:00</published><updated>2008-09-15T02:47:55.801-07:00</updated><title type='text'>MixNet software package</title><content type='html'>Estimates the parameters and hidden class variable of a Mixture of Erdös renyi Random Graphs. The estimation is performed for a Bernouilli Mixture. Packages also implement the previous post !&lt;br /&gt;&lt;br /&gt;Code : &lt;a href="http://stat.genopole.cnrs.fr/sg/software/mixnet/"&gt;native&lt;/a&gt; or &lt;a href="http://cran.r-project.org/web/packages/mixnet/index.html"&gt;R wrapper&lt;/a&gt;.&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-7021162606567818209?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/7021162606567818209/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=7021162606567818209' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/7021162606567818209'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/7021162606567818209'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2008/09/mixnet-software-package.html' title='MixNet software package'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-8245963742449759630</id><published>2008-08-22T05:40:00.000-07:00</published><updated>2008-08-22T05:44:17.223-07:00</updated><title type='text'>Fast online graph clustering via Erdős–Rényi mixture</title><content type='html'>In the context of graph clustering, we consider the problem of simultaneously estimating both the partition of the graph nodes and the parameters of an underlying mixture of affiliation networks. In numerous applications the rapid increase of data size over time makes classical clustering algorithms too slow because of the high computational cost. In such situations online clustering algorithms are an efficient alternative to classical batch algorithms. We present an original online algorithm for graph clustering based on a Erdős–Rényi graph mixture. The relevance of the algorithm is illustrated, using both simulated and real data sets. The real data set is a network extracted from the French political blogosphere and presents an interesting community organization.&lt;br /&gt;&lt;br /&gt;Read the &lt;span style="font-style:italic;"&gt;Pattern Recognition&lt;/span&gt; &lt;a href="http://dx.doi.org/10.1016/j.patcog.2008.06.019"&gt;paper.&lt;/a&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-8245963742449759630?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/8245963742449759630/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=8245963742449759630' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/8245963742449759630'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/8245963742449759630'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2008/08/fast-online-graph-clustering-via.html' title='Fast online graph clustering via Erdős–Rényi mixture'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-5242130056684591019</id><published>2007-12-03T08:31:00.000-08:00</published><updated>2007-12-03T08:37:35.933-08:00</updated><title type='text'>Mathematics for Biological Networks</title><content type='html'>The &lt;a href="http://stat.genopole.cnrs.fr/MBN2007/"&gt;"Mathematics for Biological Networks"&lt;/a&gt; Conference will be held on December 17-18 2007 at the Institut Henri Poincaré, Paris. It is a free access interdisciplinary conference in the field of network analysis focusing on applications in molecular biology. Students are encouraged to come and take part in discussions. No registration is required.&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-5242130056684591019?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/5242130056684591019/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=5242130056684591019' title='1 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/5242130056684591019'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/5242130056684591019'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2007/12/mathematics-for-biological-networks.html' title='Mathematics for Biological Networks'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>1</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-114837158123178360</id><published>2006-05-23T00:35:00.000-07:00</published><updated>2006-05-23T01:06:21.250-07:00</updated><title type='text'>Automated Metadata Hierarchy Derivation</title><content type='html'>L'&lt;a href="http://www.utc.fr/rtgi/documents/ictta06_amjad.pdf"&gt;article&lt;/a&gt; présente une méthode automatique  pour construire une hierarchie de metadata d'un ensemble de sites web sans passer par utilisation de hierarchies externes déjà prédéfinies.&lt;br /&gt;&lt;br /&gt;L'approche, dans nos expérimentation,  confirme globalement les informations issues des analyses principalement topologiques (analyse de la connectivité entre les sites) du groupe&lt;a href="http://www.utc.fr/rtgi"&gt; rtgi&lt;/a&gt; : les sites appartenant aux mêmes clusters topologiques partagent en général la même hierarchie de concepts sémantiques.&lt;br /&gt;&lt;span class="down" style="display: block;" id="formatbar_CreateLink" title="Link" onmouseover="ButtonHoverOn(this);" onmouseout="ButtonHoverOff(this);" onmouseup="" onmousedown="CheckFormatting(event);FormatbarButton('richeditorframe', this, 8);ButtonMouseDown(this);"&gt;&lt;/span&gt;&lt;br /&gt;De l'optimisation et des réglages sont en encore à étudier pour utiliser  cette méthode sur  des corpus plus importants. Il faudra donc attendre un peu avant de voir une version "flashy" sur l'&lt;a href="http://www.utc.fr/rtgi/op2007"&gt;observatoire présidentielle&lt;/a&gt;...&lt;br /&gt;&lt;br /&gt;Bravo à Amjad pour son travail et sa présentation à &lt;a href="http://ictta.enst-bretagne.fr/"&gt;Damas&lt;/a&gt;.&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-114837158123178360?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/114837158123178360/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=114837158123178360' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/114837158123178360'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/114837158123178360'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2006/05/automated-metadata-hierarchy.html' title='Automated Metadata Hierarchy Derivation'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-113749450973994691</id><published>2006-01-17T01:32:00.000-08:00</published><updated>2006-01-17T02:45:18.086-08:00</updated><title type='text'>MapReduce : parallelisation et distribution</title><content type='html'>Que faire quand l'on doit traiter un grand nombre de données et que l'on dispose uniquement de milliers de CPUs ?&lt;br /&gt;Google propose une &lt;a href="http://labs.google.com/papers/mapreduce-osdi04.pdf"&gt;architecture&lt;/a&gt; qui leur permet d'implémenter la parallelisation et la distribution de certaines de leurs tâches (machine learning, distributed sort, &lt;a href="http://labs.google.com/papers/mapreduce-osdi04-slides/index-auto-0005.html"&gt;etc&lt;/a&gt;...).  Le principe  est de spécifier une fonction &lt;span style="font-style: italic;"&gt;map&lt;/span&gt; qui calcule des paires de &lt;span style="font-style: italic;"&gt;key/value&lt;/span&gt; pour générer un ensemble de valeures intermédiaires (paires de  key/value) et une fonction &lt;span style="font-style: italic;"&gt;reduce&lt;/span&gt; qui fusionne toutes les valeures intermédiaires associées aux mêmes clés intermédiaires.&lt;span class="" style="display: block;" id="formatbar_CreateLink" title="Link" onmouseover="ButtonHoverOn(this);" onmouseout="ButtonHoverOff(this);" onmouseup="" onmousedown="CheckFormatting(event);FormatbarButton('richeditorframe', this, 8);ButtonMouseDown(this);"&gt;&lt;/span&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-113749450973994691?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/113749450973994691/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=113749450973994691' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/113749450973994691'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/113749450973994691'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2006/01/mapreduce-parallelisation-et.html' title='MapReduce : parallelisation et distribution'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-113319057138582143</id><published>2005-11-28T06:45:00.000-08:00</published><updated>2005-12-19T00:45:41.380-08:00</updated><title type='text'>Saturday Night Clever</title><content type='html'>Le old school projet CLEVER (Clientside Eigenvector Enhanced Retrieval) développé au laboratoire &lt;a href="http://www.almaden.ibm.com/almaden/"&gt;Almaden d’IBM&lt;/a&gt; a été la première tentative d’utilisation de HITS pour créer un moteur de recherche opérationnel. Deux papiers qui fixaient les bases : &lt;a href="http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=781636"&gt;Mining the Web's Link Structure&lt;/a&gt; et&lt;a href="http://theory.stanford.edu/people/raghavan/www7/181.html"&gt; &lt;span class="m"&gt;&lt;span class="l"&gt;Automatic Resource list Compilation by Analyzing Hyperlink Structure and Associated Text.&lt;/span&gt;&lt;/span&gt;&lt;/a&gt; &lt;p class="spip" align="justify"&gt;&lt;/p&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-113319057138582143?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/113319057138582143/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=113319057138582143' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/113319057138582143'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/113319057138582143'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/11/saturday-night-clever.html' title='Saturday Night Clever'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-113084622208703421</id><published>2005-11-01T03:54:00.000-08:00</published><updated>2005-11-01T03:57:02.090-08:00</updated><title type='text'>Judy, arrêtes!</title><content type='html'>Un &lt;span style="font-weight: bold;"&gt; judy array&lt;/span&gt; est une struture de données de type tableau associatif (ex: &lt;span style="font-style: italic;"&gt;hash table&lt;/span&gt;) très rapide pour le stockage et la recherche de valeurs en utilisant des clés integer ou string. Bien que ce soit une structure de données de type array, les &lt;span style="font-weight: bold;"&gt;Judy array&lt;/span&gt; peuvent avoir beaucoup d'indices non assignés. Cette structure est&lt;span style="font-style: italic;"&gt; scalable&lt;/span&gt;, performante et compacte en mémoire.&lt;br /&gt;&lt;br /&gt;Son API permet les manipulations simples (&lt;span style="font-style: italic;"&gt;insert, retrieve, delete&lt;/span&gt;) et plus complexes (&lt;span style="font-style: italic;"&gt;sort, search, count, sequencial access&lt;/span&gt;). D'une manière générale Judy (nom de la soeur de l'inventeur Doug Baskins) peut être déployée, quand le  nombre de données à stocker en mémoire est important, à la place des structures plus courantes :&lt;span style="font-style: italic;"&gt; arrays, sparse arrays, hash tables, B-trees, binary trees, linear lists&lt;/span&gt;, etc. pour les algorithmes de tri et de recherche, et les fonctions de comptage.&lt;br /&gt;Le site du projet Judy :&lt;a href="http://judy.sourceforge.net/"&gt; http://judy.sourceforge.net/&lt;/a&gt;&lt;br /&gt;L'extension perl pour utilliserJudy : &lt;a href="http://search.cpan.org/%7Ebholzman/Tie-Judy-0.03/lib/Tie/Judy.pm"&gt;Tie::Judy&lt;/a&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-113084622208703421?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/113084622208703421/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=113084622208703421' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/113084622208703421'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/113084622208703421'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/11/judy-arrtes.html' title='Judy, arrêtes!'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-112928377743696682</id><published>2005-10-14T02:38:00.000-07:00</published><updated>2005-10-30T04:52:07.846-08:00</updated><title type='text'>Document Clustering, Visualization, and Retrieval via Link Mining</title><content type='html'>&lt;ul&gt;   &lt;li&gt;Un&lt;a href="http://ise.gmu.edu/%7Esnoel/pubs/Clustering_IR_chapter_extended.pdf"&gt; article&lt;/a&gt; d'un  Raghavan (&lt;a href="http://www.cacs.louisiana.edu/%7Eraghavan/"&gt;Vijay&lt;/a&gt;). (le site  de &lt;span style="font-family:Arial;"&gt; &lt;a href="http://theory.stanford.edu/%7Epragh/"&gt;Prabhakar.&lt;/a&gt;  chercheur  à&lt;a href="http://research.yahoo.com/"&gt; &lt;/a&gt;&lt;/span&gt;&lt;a href="http://research.yahoo.com/"&gt;&lt;span style="font-family:Arial;"&gt;Yahoo! Research&lt;/span&gt;&lt;/a&gt;&lt;span style="font-family:Arial;"&gt;)&lt;/span&gt;&lt;/li&gt;   &lt;li&gt;&lt;a href="http://www.di.fc.ul.pt/tech-reports/04-11.pdf"&gt;inter-documents similarity in web search&lt;/a&gt;&lt;/li&gt;&lt;/ul&gt;Pour implémenter ces méthodes, il existe &lt;a href="http://bonsai.ims.u-tokyo.ac.jp/%7Emdehoon/software/cluster/cluster3.pdf"&gt;Cluster 3.0&lt;/a&gt; , écrit en C.  La &lt;a href="http://bonsai.ims.u-tokyo.ac.jp/%7Emdehoon/software/cluster/cluster.pdf"&gt;librairie&lt;/a&gt; est accessible depuis Perl et Python. L'interface Perl pour accéder à la librairie C est disponible sur &lt;a href="http://search.cpan.org/%7Emdehoon/Algorithm-Cluster-1.30/perl/Cluster.pm"&gt;cpan&lt;/a&gt; ou ActiveState.&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-112928377743696682?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/112928377743696682/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=112928377743696682' title='0 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112928377743696682'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112928377743696682'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/10/document-clustering-visualization-and.html' title='Document Clustering, Visualization, and Retrieval via Link Mining'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>0</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-112861283715497377</id><published>2005-10-06T08:33:00.000-07:00</published><updated>2005-10-08T03:07:26.443-07:00</updated><title type='text'>Montes dans ta chambre et révises ton C</title><content type='html'>&lt;a href="http://www.library.cornell.edu/nr/bookcpdf.html"&gt;http://www.library.cornell.edu/nr/bookcpdf.htm&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;c'est ce que me dit le valeureux thomas drugeon qui n'a rien à envier au capitaine brewster kahle. Voici une de ses carapaces vertes pour : &lt;a href="http://www.iwaw.net/05/papers/iwaw05-drugeon.pdf"&gt;A technical approach for the French Web Legal Deposit.&lt;/a&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-112861283715497377?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/112861283715497377/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=112861283715497377' title='1 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112861283715497377'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112861283715497377'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/10/montes-dans-ta-chambre-et-rvises-ton-c.html' title='Montes dans ta chambre et révises ton C'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>1</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-112803640411007037</id><published>2005-09-29T16:26:00.000-07:00</published><updated>2005-10-06T08:37:10.170-07:00</updated><title type='text'>A survey of eigenvector methods for web et autres curiosités</title><content type='html'>Un aperçu intéressant sur les trois algorithmes de classements topologiques [PageRank, Hits, Salsa] des pages/sites sur le web :&lt;a href="http://meyer.math.ncsu.edu/Meyer/PS_Files/Survey.pdf"&gt; http://meyer.math.ncsu.edu/Meyer/PS_Files/Survey.pdf.&lt;/a&gt; Les points positifs et négatifs sont également étudiés.&lt;br /&gt;&lt;br /&gt;Dans le même genre, une &lt;a href="http://meyer.math.ncsu.edu/Meyer/Talks/SIAM_CSE_2_13_05_Updating.pdf"&gt;présentation&lt;/a&gt; pour updater et trouver le vecteur stationnaire d'une chaîne irréductible de markov (PageRank et Salsa) .&lt;span style="text-decoration: underline;"&gt;&lt;/span&gt;&lt;br /&gt;&lt;br /&gt;Sinon, quelques liens qui donnent des idées...&lt;br /&gt;&lt;span style="text-decoration: underline;"&gt;&lt;/span&gt;&lt;a href="http://www.comp.hkbu.edu.hk/%7Ecib/2005/Jun/iib_vol5no1_article2.pdf"&gt;http://www.comp.hkbu.edu.hk/&lt;/a&gt;&lt;br /&gt;&lt;a href="http://www.cs.utexas.edu/users/inderjit/courses/dm2000.html"&gt;http://www.cs.utexas.edu/users/inderjit/courses/dm2000.html&lt;/a&gt;&lt;br /&gt;&lt;a href="http://genomenews.free.fr/bioinfo.html"&gt;http://genomenews.free.fr/bioinfo.html&lt;/a&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-112803640411007037?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/112803640411007037/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=112803640411007037' title='3 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112803640411007037'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112803640411007037'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/09/survey-of-eigenvector-methods-for-web.html' title='A survey of eigenvector methods for web et autres curiosités'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>3</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-112746211914594468</id><published>2005-09-23T00:46:00.000-07:00</published><updated>2005-09-28T01:19:55.590-07:00</updated><title type='text'>Bloom filter</title><content type='html'>&lt;p&gt;Le &lt;b&gt;Bloom filter&lt;/b&gt;, a été pensé par Burton H.Bloom en 1970. C'est une structure de données, probabiliste, compacte en mémoire, qui est utilisée pour renseigner si un élément est présent ou non dans un ensemble. &lt;a href="http://en.wikipedia.org/wiki/False_positive"&gt;Les false positives&lt;/a&gt; sont possibles mais pas les &lt;a href="http://en.wikipedia.org/wiki/False_negative"&gt;false negatives&lt;/a&gt;. Les élements peuvent uniquement être ajoutés au set, ils ne peuvent pas être enlevés. Plus il y a d'élements dans le set, plus la probablilité d'avoir des false positives est grande.&lt;/p&gt; &lt;p&gt;Le Bloom filter peut être utilisé ainsi dans de nombreuses situations : détection de la langue en vérifiant l'appartenance à un dictionnaire, marquage d'urls pour les crawlers afin de ne pas visiter deux fois les mêmes pages, etc.&lt;br /&gt;&lt;/p&gt; &lt;ul&gt;   &lt;li&gt;Des compléments sur le bloom filter sur &lt;a href="http://en.wikipedia.org/wiki/Bloom_filter"&gt;Wikipedia&lt;/a&gt;.&lt;/li&gt;   &lt;li&gt;Utiliser des bloom en &lt;a href="http://www.perl.com/pub/a/2004/04/08/bloom_filters.html"&gt;perl&lt;/a&gt;.&lt;/li&gt;   &lt;li&gt;Ajuster ces &lt;a href="http://www.cc.gatech.edu/fac/Pete.Manolios/bloom-filters/calculator.html"&gt;paramètres&lt;/a&gt;.&lt;/li&gt; &lt;/ul&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-112746211914594468?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/112746211914594468/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=112746211914594468' title='2 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112746211914594468'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112746211914594468'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/09/bloom-filter.html' title='Bloom filter'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>2</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-112714533094506197</id><published>2005-09-19T08:41:00.000-07:00</published><updated>2005-10-04T15:58:37.536-07:00</updated><title type='text'>trier et manipuler les listes et scalaires en perl</title><content type='html'>&lt;ul&gt;   &lt;li&gt;Le module &lt;a href="http://search.cpan.org/dist/Sort-Maker/Sort/Maker.pm"&gt;Sort::Maker&lt;/a&gt;  permet d'une manière simple et efficace de concevoir des fonctions de tris.  L'&lt;a href="http://web.archive.org/web/20041010090509/http://www.sysarch.com/perl/sort_paper.html"&gt;article&lt;/a&gt; de l'auteur &lt;span style="font-size:100%;"&gt;Uri Guttman.&lt;/span&gt;&lt;br /&gt;&lt;/li&gt;   &lt;li&gt;Pour les traitements rapides de listes &lt;a href="http://search.cpan.org/%7Egbarr/Scalar-List-Utils-1.17/lib/List/Util.pm"&gt;List::Util et &lt;/a&gt;&lt;a href="http://search.cpan.org/%7Evparseval/List-MoreUtils-0.10/lib/List/MoreUtils.pm"&gt;List::MoreUtils.&lt;/a&gt;&lt;/li&gt;&lt;li style="color: rgb(0, 0, 0);"&gt;&lt;span style="font-size:100%;"&gt;&lt;span style="font-family:Microsoft Sans Serif;"&gt;Le petit frère de List::Utils, pour les scalars &lt;/span&gt;&lt;/span&gt;&lt;a href="http://search.cpan.org/%7Egbarr/Scalar-List-Utils-1.17/lib/Scalar/Util.pm"&gt;Scalar::Util.&lt;/a&gt;&lt;/li&gt;   &lt;li style="color: rgb(0, 0, 0);"&gt;Le module &lt;a href="http://search.cpan.org/%7Eewijaya/Sort-Radix-0.04/lib/Sort/Radix.pm"&gt;Sort::Radix&lt;/a&gt; permet de trier en&lt;span style="font-size:100%;"&gt;&lt;span style="color: rgb(0, 0, 255);"&gt;&lt;span style="font-family:Microsoft Sans Serif;"&gt; &lt;span style="color: rgb(0, 0, 0);"&gt;O(n * k) &lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;span style="color: rgb(0, 0, 0);font-size:100%;" &gt;&lt;span style="font-family:Microsoft Sans Serif;"&gt;avec k la taille fixe des éléments à trier.&lt;/span&gt;&lt;/span&gt;&lt;/li&gt;   &lt;li style="color: rgb(0, 0, 0);"&gt;&lt;span style="color: rgb(0, 0, 0);font-size:100%;" &gt;&lt;span style="font-family:Microsoft Sans Serif;"&gt;Le module&lt;a href="http://search.cpan.org/%7Ecreamyg/Sort-External-0.10/lib/Sort/External.pm"&gt; Sort::External&lt;/a&gt; permet de trier des listes ne pouvant pas tenir en mémoire vive en stockant les listes sur différents fichiers temporaires puis en les fusionnant.&lt;/span&gt;&lt;/span&gt;&lt;/li&gt;&lt;li style="color: rgb(0, 0, 0);"&gt;Finalement le module qui tue :&lt;a href="http://search.cpan.org/%7Esalva/Sort-Key-0.13/lib/Sort/Key.pm"&gt; Sort-Key-0.13&lt;/a&gt; &lt;br /&gt;  &lt;/li&gt;   &lt;/ul&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-112714533094506197?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/112714533094506197/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=112714533094506197' title='2 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112714533094506197'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112714533094506197'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/09/trier-et-manipuler-les-listes-et.html' title='trier et manipuler les listes et scalaires en perl'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>2</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-112712828190904186</id><published>2005-09-19T04:01:00.000-07:00</published><updated>2005-09-19T04:18:01.100-07:00</updated><title type='text'>Mining the Web: Discovering Knowledge from Hypertext Data</title><content type='html'>La page de &lt;a href="http://www.cse.iitb.ac.in/%7Esoumen/"&gt;Soumen Chakrabarti&lt;/a&gt;, auteur du livre &lt;span style="font-style: italic;"&gt;Mining the Web, &lt;/span&gt; apporte des compléments sur ses recherches en mettant à disposition ses publications et quelques logiciels. Les transparents de ses cours sont également disponibles.&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-112712828190904186?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/112712828190904186/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=112712828190904186' title='1 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112712828190904186'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112712828190904186'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/09/mining-web-discovering-knowledge-from.html' title='Mining the Web: Discovering Knowledge from Hypertext Data'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>1</thr:total></entry><entry><id>tag:blogger.com,1999:blog-10230918.post-112695807557980431</id><published>2005-09-17T04:53:00.000-07:00</published><updated>2005-09-18T08:30:29.116-07:00</updated><title type='text'>I'm back on the web</title><content type='html'>&lt;span style="color: rgb(0, 0, 0);font-family:Verdana,Arial,Helvetica,sans-serif;font-size:100%;"  &gt; physically and mentally...&lt;/span&gt;&lt;div class="blogger-post-footer"&gt;&lt;img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/10230918-112695807557980431?l=funkybeat.blogspot.com' alt='' /&gt;&lt;/div&gt;</content><link rel='replies' type='application/atom+xml' href='http://funkybeat.blogspot.com/feeds/112695807557980431/comments/default' title='Publier les commentaires'/><link rel='replies' type='text/html' href='http://www.blogger.com/comment.g?blogID=10230918&amp;postID=112695807557980431' title='2 commentaires'/><link rel='edit' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112695807557980431'/><link rel='self' type='application/atom+xml' href='http://www.blogger.com/feeds/10230918/posts/default/112695807557980431'/><link rel='alternate' type='text/html' href='http://funkybeat.blogspot.com/2005/09/im-back-on-web.html' title='I&apos;m back on the web'/><author><name>hugo</name><uri>http://www.blogger.com/profile/07758670784675946136</uri><email>noreply@blogger.com</email><gd:image rel='http://schemas.google.com/g/2005#thumbnail' width='32' height='32' src='http://1.bp.blogspot.com/__knvamoEAiA/SK61VVcbtJI/AAAAAAAAAKM/cLEnwfVsBCM/S220/_cprg8IO-fO9G64YlhErrc3-SdL227lk82WRR0pFtPxda1ttFxjcb9rKF26AiBnn.jpeg'/></author><thr:total>2</thr:total></entry></feed>
