Abstract:
Connectionist network learning of context free languages has so far been applied only to very simple cases and has often made use of an external stack. Learning complex context free languages with a homogeneous neural mechanism looks like a much harder problem. The current paper takes a step toward solving this problem by analyzing context free grammar computation (without addressing learning) in a class of analog computers called Dynamical Automata, which are naturally implemented in connectionist networks. The result is a widely applicable method of using fractal sets to organize infinite state computations in a bounded state space. An appealing consquence is the development of parameter-space maps which locate various complex computers in spatial relationships to one another. An example suggests that such a global perspective on the organization of the parameter space may be helpful for solving the hard problem of getting connectionist networks to learn complex grammars from examples. Section
Citations
|
2869
|
Introduction to Automata Theory, Languages and Computation
– Hopcroft, Ullman
- 1979
|
|
1127
|
Finding structure in time
– Elman
- 1990
|
|
464
|
Fractals everywhere
– Barnsley
- 1988
|
|
307
|
On a theory of computation and complexity over the real numbers
– Blum, Shub, et al.
- 1989
|
|
226
|
Distributed representations, simple recurrent networks, and grammatical structure
– Elman
- 1991
|
|
199
|
The induction of dynamical recognizers
– Pollack
- 1991
|
|
151
|
Nonlinear Dynamics and Chaos
– Strogatz
|
|
75
|
Computation at the onset of chaos
– Crutchfield, Young
- 1990
|
|
70
|
N.: The power of amnesia
– Ron, Singer, et al.
- 1994
|
|
48
|
Higher order recurrent networks and grammatical inference
– Giles, Sun, et al.
- 1990
|
|
48
|
Turing computability with neural nets
– Siegelmann, Sontag
- 1991
|
|
24
|
A Theory of Grammatical Induction in the Connectionist Paradigm
– Kremer
- 1996
|
|
21
|
Using prior knowledge in an NNPDA to learn context-free languages
– Das, Giles, et al.
- 1992
|
|
21
|
Spatial representation of symbolic sequences through iterative function systems
– Tino
- 1999
|
|
20
|
On the computational power of dynamical systems and hybrid systems
– Bournez, Cosnard
- 1996
|
|
15
|
A connectionist symbol manipulator that discovers the structure of context-free languages
– Mozer, Das
- 1993
|
|
11
|
The simple dynamics of super Turing theories
– Siegelmann
- 1996
|
|
11
|
Landscapes in recurrent networks
– Wiles, Elman
- 1995
|
|
10
|
Dynamical automata
– Tabor
- 1998
|
|
6
|
Constructing finite-context sources from fractal representations of symbolic sequences
– Tino, Dorffner
- 1998
|
|
5
|
The calculi of emergence: Computation, dynamics, and induction. Physica D, 75:11--54
– Crutchfield
- 1994
|
|
4
|
Recursion theory on the reals and continuous time computation
– Moore
- 1996
|
|
3
|
Representing the structure of a simple context-free language in a recurrent neural network: A dynamical systems approach
– Rodriguez
- 1995
|
