MAXNET is a common competitive architecture to select the maximum or m
inimum from a set of data. However, there are two major problems with
the MAXNET. The first problem is its slow convergence rate if all the
data have nearly the same value. The second one is that it fails when
either nonunique extreme values exist or each initial value is smaller
than or equal to the sum of initial inhibitions from other nodes. In
this paper, a novel neural network model called SELECTRON is proposed
to select the maxima or minima from a set of data. This model is able
to select all the maxima or minima via competition among the processin
g units even when MAXNET fails. We will then prove that SELECTRON conv
erges to the correct state in every situation. In addition, the conver
gence rates of SELECTRON for three special data distributions will be
derived. Finally, simulation results indicate that SELECTRON converges
much faster than MAXNET.