🚀 go-pugleaf

              The International Computer Science Institute
                     is pleased to present a talk:

                  Tuesday, August 11, 1992  2:00 p.m.

                              KLAUS JANTKE
                                  ICSI

 ``Formalizations in Case-Based Reasoning: Inductive Inference Results''

           There is proposed a formalization of case-based reason-
      ing  in  terms  of  recursion-theoretic inductive inference.
      This approach is directly derived from  some  recently  pub-
      lished  case-based learning algorithms. The intention of the
      talk is  to  exhibit  the  relationship  between  case-based
      learning  and  inductive  inference with mathematical preci-
      sion.

           In particular, it is the author's intention  to  invoke
      inductive  inference  results and techniques for pointing to
      the crucial questions in case-based reasoning.

           There are formalized several approaches  to  case-based
      learning. First, they vary in the way of of presenting cases
      to a  learning  system.  Second,  they  are  different  with
      respect  to  the underlying semantics of case bases together
      with similarity measures. Third, they are  distinguished  by
      the flexibility in using similarity functions.

           The  investigations  presented  relate  the  introduced
      learning   types   to  identification  types  in  recursion-
      theoretic inductive inference.

        This talk will be held in the Main Lecture Hall at ICSI.
          1947 Center Street, Sixth Floor, Berkeley, CA 94704
       (On Center between Milvia and Martin Luther King Jr. Way)

      ----------------------------------------------------------
      Requests to be added to or deleted from the "talk" mailing 
      list should be directed to talk-request@icsi.Berkeley.EDU.
      ----------------------------------------------------------