paper on Imax

[R URBANCZIK]

The following paper (12 pages, submitted to Europhysics letters)
is available online from: 

http://neural-server.aston.ac.uk/Papers/postscript/NCRG_1999_033.ps.Z


    Statistical Mechanics of Mutual Information Maximization

    R. Urbanczik,  Neural Computing Research Group, Aston University


    Abstract:

    An unsupervised learning procedure based on maximizing the mutual
    information between the outputs of two networks receiving different
    but statistically dependent inputs is analyzed  (Becker and Hinton,
    Nature, 355, 92, 161).  By exploiting a formal analogy to supervised
    learning in parity machines, the theory of zero temperature Gibbs
    learning for the unsupervised procedure is presented for the case that
    the  networks  are perceptrons and for the case of fully connected 
    committees.