<section name="raw">
    <SEQUENTIAL>
      <record key="001" att1="001" value="LIB900212007" att2="LIB900212007">001   LIB900212007</record>
      <field key="037" subkey="x">englisch</field>
      <field key="050" subkey="x">Forschungsbericht</field>
      <field key="076" subkey="">Formalwissenschaft</field>
      <field key="079" subkey="y">http://www.ihs.ac.at/publications/ihsfo/fo32.pdf</field>
      <field key="079" subkey="z">janac, karel, adaptive stochastic approximations (pdf)</field>
      <field key="100" subkey="">janac, karel</field>
      <field key="331" subkey="">adaptive stochastic approximations</field>
      <field key="403" subkey="">1. ed.</field>
      <field key="410" subkey="">wien</field>
      <field key="412" subkey="">institut fuer hoehere studien</field>
      <field key="425" subkey="">1969, january</field>
      <field key="433" subkey="">14 pp.</field>
      <field key="451" subkey="">institut fuer hoehere studien; forschungsberichte; 32</field>
      <field key="544" subkey="">IHSFO 32</field>
      <field key="753" subkey="">abstract (abridged): many of the present problems in automatic control economic systems and living organism can be converted to</field>
      <field key="par" subkey="a">meter optimization in stochastic systems. foremost among these problems are questions of the control of systems with</field>
      <field key="inc" subkey="o">mplete information, learning problems, adaptive control, identification of objects, and the automatic synthesis of objects.</field>
      <field key="suc" subkey="h">problems can be solved by stochastic approximation methods which are, essentially, iterative procedures. for this reason,</field>
      <field key="gre" subkey="a">t attention is paid to these methods in connection with practical applications. they were elaborated as a purely mathematical</field>
      <field key="pro" subkey="b">lem a long time ago and a number of valuable results are now available. not only the conditions of convergence,but some</field>
      <field key="pro" subkey="p">erties of the asymptotic speed of convergence are also known. in some cases, however, a disadvantage of stochastic</field>
      <field key="app" subkey="r">oximations is the slow convergence to the desired extreme of the optimality criterion. at present, utmost attention is</field>
      <field key="dev" subkey="o">ted to the elimination of these undesirable properties. unfortunately, practical requirements are often in disagreement with</field>
      <field key="the" subkey="">assumptions from which we start when seeking more effective algorithms. (...);</field>
    </SEQUENTIAL>
  </section>