Extracting automata from recurrent neural networks using queries and counterexamples
We present a novel algorithm that uses exact learning and abstraction to extract a
deterministic finite automaton describing the state dynamics of a given trained RNN. We do …
deterministic finite automaton describing the state dynamics of a given trained RNN. We do …
First-order recurrent neural networks and deterministic finite state automata
P Manolios, R Fanelli - Neural Computation, 1994 - ieeexplore.ieee.org
We examine the correspondence between first-order recurrent neural networks and
deterministic finite state automata. We begin with the problem of inducing deterministic finite …
deterministic finite state automata. We begin with the problem of inducing deterministic finite …
Learning and extracting finite state automata with second-order recurrent neural networks
CL Giles, CB Miller, D Chen, HH Chen, GZ Sun… - Neural …, 1992 - direct.mit.edu
We show that a recurrent, second-order neural network using a real-time, forward training
algorithm readily learns to infer small regular grammars from positive and negative string …
algorithm readily learns to infer small regular grammars from positive and negative string …
Learning finite state machines with self-clustering recurrent networks
Z Zeng, RM Goodman, P Smyth - Neural Computation, 1993 - ieeexplore.ieee.org
Recent work has shown that recurrent neural networks have the ability to learn finite state
automata from examples. In particular, networks using second-order units have been …
automata from examples. In particular, networks using second-order units have been …
Induction of finite-state automata using second-order recurrent networks
R Watrous, G Kuhn - Advances in neural information …, 1991 - proceedings.neurips.cc
Second-order recurrent networks that recognize simple finite state lan (cid: 173) guages
over {0, 1}* are induced from positive and negative examples. Us (cid: 173) ing the complete …
over {0, 1}* are induced from positive and negative examples. Us (cid: 173) ing the complete …
Extraction of rules from discrete-time recurrent neural networks
The extraction of symbolic knowledge from trained neural networks and the direct encoding
of (partial) knowledge into networks prior to training are important issues. They allow the …
of (partial) knowledge into networks prior to training are important issues. They allow the …
Noisy time series prediction using recurrent neural networks and grammatical inference
Financial forecasting is an example of a signal processing problem which is challenging due
to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have …
to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have …
Learning deterministic weighted automata with queries and counterexamples
We present an algorithm for reconstruction of a probabilistic deterministic finite automaton
(PDFA) from a given black-box language model, such as a recurrent neural network (RNN) …
(PDFA) from a given black-box language model, such as a recurrent neural network (RNN) …
Representation of finite state automata in recurrent radial basis function networks
In this paper, we propose some techniques for injecting finite state automata into Recurrent
Radial Basis Function networks (R2BF). When providing proper hints and constraining the …
Radial Basis Function networks (R2BF). When providing proper hints and constraining the …
An analysis of noise in recurrent neural networks: convergence and generalization
Concerns the effect of noise on the performance of feedforward neural nets. We introduce
and analyze various methods of injecting synaptic noise into dynamically driven recurrent …
and analyze various methods of injecting synaptic noise into dynamically driven recurrent …