scholarly journals An Algebraic Framework to Represent Finite State Machines in Single-Layer Recurrent Neural Networks

1995 ◽  
Vol 7 (5) ◽  
pp. 931-949 ◽  
Author(s):  
R. Alquézar ◽  
A. Sanfeliu
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Single Layer ◽  
Finite State Machines ◽  
Grammatical Inference ◽  
State Machines ◽  
Linear System Of Equations ◽  
Wide Range ◽  
Finite State ◽  
Algebraic Framework

In this paper we present an algebraic framework to represent finite state machines (FSMs) in single-layer recurrent neural networks (SLRNNs), which unifies and generalizes some of the previous proposals. This framework is based on the formulation of both the state transition function and the output function of an FSM as a linear system of equations, and it permits an analytical explanation of the representational capabilities of first-order and higher-order SLRNNs. The framework can be used to insert symbolic knowledge in RNNs prior to learning from examples and to keep this knowledge while training the network. This approach is valid for a wide range of activation functions, whenever some stability conditions are met. The framework has already been used in practice in a hybrid method for grammatical inference reported elsewhere (Sanfeliu and Alquézar 1994).

scholarly journals The Influence of Context on the Learning of Metrical Stress Systems Using Finite-State Machines

2018 ◽  
Vol 44 (2) ◽  
pp. 329-348
Author(s):  
Cesko Voeten ◽  
Menno van Zaanen
Keyword(s):  
Finite State Machines ◽  
Learning System ◽  
Grammatical Inference ◽  
Finite State Automata ◽  
State Machines ◽  
System A ◽  
Wide Range ◽  
The Family ◽  
Finite State ◽  
Stress Patterns

Languages vary in the way stress is assigned to syllables within words. This article investigates the learnability of stress systems in a wide range of languages. The stress systems can be described using finite-state automata with symbols indicating levels of stress (primary, secondary, or no stress). Finite-state automata have been the focus of research in the area of grammatical inference for some time now. It has been shown that finite-state machines are learnable from examples using state-merging. One such approach, which aims to learn k-testable languages, has been applied to stress systems with some success. The family of k-testable languages has been shown to be efficiently learnable (in polynomial time). Here, we extend this approach to k, l-local languages by taking not only left context, but also right context, into account. We consider empirical results testing the performance of our learner using various amounts of context (corresponding to varying definitions of phonological locality). Our results show that our approach of learning stress patterns using state-merging is more reliant on left context than on right context. Additionally, some stress systems fail to be learned by our learner using either the left-context k-testable or the left-and-right-context k, l-local learning system. A more complex merging strategy, and hence grammar representation, is required for these stress systems.

scholarly journals Pioneer: A New Tool for Coding of Multi-Level Finite State Machines Based on Evolution Programming

VLSI Design ◽  
1994 ◽  
Vol 2 (2) ◽  
pp. 105-116
Author(s):  
S. Muddappa ◽  
R. Z. Makki ◽  
Z. Michalewicz ◽  
S. Isukapalli
Keyword(s):  
Finite State Machines ◽  
Mutation Rates ◽  
Natural Phenomenon ◽  
State Machines ◽  
State Assignment ◽  
Wide Range ◽  
Finite State ◽  
Multi Level ◽  
Crossover And Mutation ◽  
Evolution Programs

In this paper we present a new tool for the encoding of multi-level finite state machines based on the concept of evolution programming. Evolution programs are stochastic adaptive algorithms, based on the paradigm of genetic algorithms whose search methods model some natural phenomenon: genetic inheritance and Darwinian strife for survival. Crossover and mutation rates were tailored to the state assignment problem experimentally. We present results over a wide range of MCNC benchmarks which demonstrate the effectiveness of the new tool. The results show that evolution programs can be effectively applied to state assignment.

EXPERIMENTAL COMPARISON OF THE EFFECT OF ORDER IN RECURRENT NEURAL NETWORKS

1993 ◽  
Vol 07 (04) ◽  
pp. 849-872 ◽  
Author(s):  
CLIFFORD B. MILLER ◽  
C. LEE GILES
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Internal State ◽  
Second Order ◽  
Convergence Time ◽  
Experimental Comparison ◽  
Grammatical Inference ◽  
Neural Net ◽  
First Order ◽  
Finite State

There has been much interest in increasing the computational power of neural networks. In addition there has been much interest in “designing” neural networks better suited to particular problems. Increasing the “order” of the connectivity of a neural network permits both. Though order has played a significant role in feedforward neural networks, its role in dynamically driven recurrent networks is still being understood. This work explores the effect of order in learning grammars. We present an experimental comparison of first order and second order recurrent neural networks, as applied to the task of grammatical inference. We show that for the small grammars studied these two neural net architectures have comparable learning and generalization power, and that both are reasonably capable of extracting the correct finite state automata for the language in question. However, for a larger randomly-generated ten-state grammar, second order networks significantly outperformed the first order networks, both in convergence time and generalization capability. We show that these networks learn faster the more neurons they have (our experiments used up to 10 hidden neurons), but that the solutions found by smaller networks are usually of better quality (in terms of generalization performance after training). Second order nets have the advantage that they converge more quickly to a solution and can find it more reliably than first order nets, but that the second order solutions tend to be of poorer quality than those of the first order if both architectures are trained to the same error tolerance. Despite this, second order nets can more successfully extract finite state machines using heuristic clustering techniques applied to the internal state representations. We speculate that this may be due to restrictions on the ability of first order architecture to fully make use of its internal state representation power and that this may have implications for the performance of the two architectures when scaled up to larger problems.

Time-delay neural networks: representation and induction of finite-state machines

1997 ◽  
Vol 8 (5) ◽  
pp. 1065-1070 ◽  
Author(s):  
D.S. Clouse ◽  
C.L. Giles ◽  
B.G. Horne ◽  
G.W. Cottrell
Keyword(s):  
Neural Networks ◽  
Time Delay ◽  
Finite State Machines ◽  
State Machines ◽  
Finite State

scholarly journals Efficient parallel derivation of short distinguishing sequences for nondeterministic finite state machines using MapReduce

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Bilal Elghadyry ◽  
Faissal Ouardi ◽  
Zineb Lotfi ◽  
Sébastien Verel
Keyword(s):  
Finite State Machine ◽  
Exact Algorithm ◽  
Finite State Machines ◽  
Identification Problem ◽  
State Machine ◽  
State Machines ◽  
State Identification ◽  
Distinguishing Sequences ◽  
Wide Range ◽  
Finite State

AbstractDistinguishing sequences are widely used in finite state machine-based conformance testing to solve the state identification problem. In this paper, we address the scalability issue encountered while deriving distinguishing sequences from complete observable nondeterministic finite state machines by introducing a massively parallel MapReduce version of the well-known Exact Algorithm. To the best of our knowledge, this is the first study to tackle this task using the MapReduce approach. First, we give a concise overview of the well-known Exact Algorithm for deriving distinguishing sequences from nondeterministic finite state machines. Second, we propose a parallel algorithm for this problem using the MapReduce approach and analyze its communication cost using Afrati et al. model. Furthermore, we conduct a variety of intensive and comparative experiments on a wide range of finite state machine classes to demonstrate that our proposed solution is efficient and scalable.

Sign in / Sign up

Export Citation Format

Share Document