Next: DTRNN based on sigmoid
Up: DTRNN based on threshold
Previous: #horne96j###:
  Contents
  Index
These authors
(http://www.dlsi.ua.es/~mlf/nnafmc/papers/goudreau94first.pdf)
study whether simple single-layer DTRNN (neural Moore
machines, see section 3.2.2)
with threshold linear units (TLU) are
capable of representing finite-state
recognizers or DFA. Their study shows that,
- when the output of the neural Moore machine is
simply a projection of the state , first-order
DTRNN are not capable of representing some DFA,
whereas second-order
DTRNN
may represent any DFA, and
- when the output is computed by a
single-layer feedforward neural
network (as in
Elman (1990) nets), then first-order
DTRNN may
represent any DFA provided that some of the states (not all of them)
in the DFA are represented by more than one state unit in the DTRNN, which
Goudreau et al. (1994) call state-splitting (see
section 4.2.2).
Complete splitting would lead to
state units, as in
the construction by Minsky (1967) , but the
authors show an example where less units are used. With second-order
networks, state-splitting is not necessary and units are
sufficient.
Next: DTRNN based on sigmoid
Up: DTRNN based on threshold
Previous: #horne96j###:
  Contents
  Index
Debian User
2002-01-21