Next: #Alo91a###:
Up: DTRNN based on threshold
Previous: DTRNN based on threshold
  Contents
  Index
This paper generalizes
the result by Minsky (1967) by showing that
TLU-based
Elman (1990) nets may actually represent finite
automata using
states,5.4 but
the construction by Kremer (1995)
allows for
input and output
symbols to be represented by
arbitrary patterns of `0' and `1' activations (instead of being
represented by exclusive or one-hot patterns having
precisely one `1'). This has the effect of reducing the number of
learnable parameters in the input-state
() and the state-output ( weight
matrices (see section 3.2.2).
Debian User
2002-01-21