Paper: Query learning in committee machine

[P Sollich]

FTP-host: archive.cis.ohio-state.edu
FTP-filename: /pub/neuroprose/sollich.queries_comm_machine.ps.Z

Dear connectionists, 

the following preprint is now available for copying from the neuroprose
repository:

                   Learning from Minimum Entropy Queries 
                        in a Large Committee Machine

                              Peter Sollich
                          Department of Physics
                         University of Edinburgh
                          Edinburgh EH9 3JZ, U.K.

                                 ABSTRACT
 
   In supervised learning, the redundancy contained in random examples can
   be avoided by learning from queries.  Using statistical mechanics, we
   study learning from minimum entropy queries in a large tree-committee
   machine.  The generalization error decreases exponentially with the
   number of training examples, providing a significant improvement over
   the algebraic decay for random examples.  The connection between entropy
   and generalization error in multi-layer networks is discussed, and a
   computationally cheap algorithm for constructing queries is suggested
   and analysed. 

Has appeared in Physical Review E, 53, R2060--R2063, 1996 (4 pages).
Comments and/or feedback are welcome. 

Peter Sollich


PS: Sorry - no hardcopies available.

--------------------------------------------------------------------------
 Peter Sollich                           Department of Physics
                                         University of Edinburgh
 e-mail: P.Sollich at ed.ac.uk              Kings Buildings
 phone: +44 - (0)131 - 650 5293          Mayfield Road
                                         Edinburgh EH9 3JZ, U.K.
--------------------------------------------------------------------------