<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd">
  <channel>
    <title>Perlaza, Samir M. (1985-....)</title>
    <description><![CDATA[ Titulaire d'un doctorat en électronique et communications de Télécom ParisTech (2011)

Chargé de Recherche, Centre Inria d'Université Côte d'Azur,  Sophia Antipolis, France. Chercheur Associé au Laboratoire de Géométrie Algébrique et Applications à la Théorie de l’Information (GAATI), Université de la Polynésie Française, Faaa, French Polynesia. Visiting Research Collaborator, Department of Electrical and Computer Engineering, Princeton University, Princeton, New Jersey, USA.

Directeur et membr ]]></description>
    <link>https://www.canal-u.tv/intervenants/perlaza-samir-m-197827136</link>
    <lastBuildDate>Wed, 08 Jun 2022 17:08:39 +0100</lastBuildDate>
    <generator>Canal-U</generator>
    <language>fr</language>
          <image>
        <url>https://www.canal-u.tv/sites/default/files/styles/carre_1400/public/medias/images/intervenant/2024/10/DSC_0141%20%2015x21.jpeg?h=97003be6&amp;itok=MkfMubHZ</url>
        <title>Perlaza, Samir M. (1985-....)</title>
        <link>https://www.canal-u.tv/intervenants/perlaza-samir-m-197827136</link>
      </image>
        <itunes:category text="Education"></itunes:category>
    <itunes:author >Canal-U</itunes:author>
    <itunes:explicit >No</itunes:explicit>
    <itunes:owner >
      <itunes:name>Perlaza, Samir M. (1985-....)</itunes:name>
      <itunes:email>contact@canal-u.tv</itunes:email>
    </itunes:owner>
          <item>
        <title>FOUNDS Seminar Series Talk 13 - Generalization Error of Machine Learning Algorithms</title>
        <link>https://www.canal-u.tv/157445</link>
                  <description><![CDATA[ In this talk, the method of gaps, a technique for deriving closed-form expressions for the generalization error of machine learning algorithms in terms of information measures is introduced. The method relies on two central observations: (a) The generalization error is an average of the variation of the expected empirical risk with respect to changes on the probability measure (used for expectation); and (b) these variations, also referred to as gaps, exhibit closed-form expressions in terms of  ]]></description>
                          <pubDate>Fri, 25 Oct 2024 20:03:53 +0100</pubDate>
                <guid isPermaLink="false">https://www.canal-u.tv/157445</guid>
                  <enclosure url="https://vod.canal-u.tv/hls/2024/10/100649/perlaza-funds2024,_480.mp4,_240.mp4,.urlset/master.m3u8" length="3557" type="application/x-mpegurl" />
                      </item>
      </channel>
</rss>
