paper available in neuroprose

[Holm Schwarze]

** DO NOT FORWARD TO OTHER GROUPS **

The following paper has been placed in the Neuroprose archive in file 
schwarze.committee.ps.Z . Retrieval instructions follow the abstract. 
Hardcopies are not available.

-- Holm Schwarze (holm at nordita.dk)

-------------------------------------------------------------------------

	 GENERALIZATION IN FULLY CONNECTED COMMITTEE MACHINES

		    H. Schwarze and J. Hertz  
	   CONNECT, The Niels Bohr Institute and Nordita 
            Blegdamsvej 17, DK-2100 Copenhagen, Denmark 

                          ABSTRACT

We study supervised learning in a fully connected committee machine
trained to implement a rule of the same structure. The generalization
error as a function of the number of training examples per weight is
calculated within the annealed approximation. For binary weights we
find a discontinuous transition from poor to perfect generalization.
Beyond this transition metastable states exist even for large training
sets. The scaling of the order parameters with the number of hidden
units depends on the size of the training set. For continuous weights
we find a discontinuous transition from a committee--symmetric solution 
to one with specialized hidden units.

-------------------------------------------------------------------------

To retrieve the paper by anonymous ftp:

        unix> ftp archive.cis.ohio-state.edu  # (128.146.8.52)
        Name: anonymous
        Password: neuron
        ftp> cd pub/neuroprose
        ftp> binary
        ftp> get schwarze.committee.ps.Z
        ftp> quit
        unix> uncompress schwarze.committee.ps.Z
        unix> lpr -P <printer name> schwarze.committee.ps
-------------------------------------------------------------------------