Next: Index
Up: Inference of context-free grammars
Previous: #Mozer93p###
  Contents
  Index
describe a method --partially
described earlier in (Zeng et al., 1993)-- to use and train a second-order
DTRNN such as
the one used by Giles et al. (1992) , without and with an
external stack, so that
stable finite-state
or pushdown
automaton behavior are
ensured. The method has two basic ingredients: (a) a discretization
function
which is applied after the sigmoid
function when computing the new
state of the DTRNN, and (b) a pseudo-gradient
learning method, which may be intuitively described as
follows: the RTRL
formulas are written for the corresponding second-order
DTRNN without the discretization function (as in
(Giles et al., 1992)) but used with discretized states
instead. The resulting algorithm is empirically
investigated to characterize its learning behavior; the
conclusion is that, even if it does not guarantee the
reduction of the error, the algorithm is able to train the
DTRNN to perform the task. One of the advantages of the
discretization
is that FSM extraction is trivial: each FSM state is
represented by a single point in state
space.
Special error functions and
learning strategies are used for the case in which the
DTRNN manipulates an external stack
for the recognition of a subset of
context-free
languages
(the stack alphabet is taken to be the same as the input
alphabet and transitions consuming no input are not
allowed; unlike
Giles et al. (1990), these authors use a discrete external
stack).
Next: Index
Up: Inference of context-free grammars
Previous: #Mozer93p###
  Contents
  Index
Debian User
2002-01-21