Next: Inference of context-free grammars
Up: Inference of finite-state machines
Previous: #tino95j###
  Contents
  Index
(http://www.dlsi.ua.es/~mlf/nnafmc/papers/sreerupa98dynamic.pdf) encourage a second-order
DTRNN (similar to the ones used by
Giles et al. (1992)) to adopt a finite-state like
behavior by means of clustering
methods, which may be unsupervised or supervised. In the first case,
unsupervised clustering of the points of state space visited by the network is used after a
certain number of training epochs and a new next-state
function is constructed as follows: first,
a next state candidate is computed from
using eq. 3.8; then, it is assigned to the corresponding
cluster; finally, it is linearly combined with the corresponding
centroid to obtain the next state:
, with
estimated from the current error. In the second
(supervised) case, states are assumed to be ideally fixed
points but actually corrupted by noise that
follows a Gaussian distribution whose mean and variance is estimated
for each state simultaneously to the weights of the DTRNN. The method
assumes a known number of states and uses a temperature parameter to
gradually shrink the Gaussians as the error improves. In the
experiments, both the supervised and unsupervised approaches improve
the results obtained without using any clustering; the supervised
clustering method performs much better than the unsupervised one. The
idea of using clustering to improve FSM learning by
DTRNN had
been previously reported by Das and Das (1991) and Das and Mozer (1994).
Next: Inference of context-free grammars
Up: Inference of finite-state machines
Previous: #tino95j###
  Contents
  Index
Debian User
2002-01-21