Neuro-fuzzy systems- the combination of artificial neural networks with fuzzy logic- have become useful in many application domains. However, conventional neuro-fuzzy models usually need enhanced representational power for applications that require context and state (e.g., speech, time series prediction, control). Some of these applications can be readily modeled as finite state automata. Previously, it was proved that deterministic finite state automata (DFA) can be synthesized by or mapped into recurrent neural networks by directly programming the DFA structure into the weights of the neural network. Based on those results, a synthesis method is proposed for mapping fuzzy finite state automata (FFA) into recurrent neural networks. Furthermore, this mapping is suitable for direct implementation in VLSI, i.e. the encoding of FFA as a generalization of the encoding of DFA in VLSI systems. The synthesis method requires FFA to undergo a transformation prior to being mapped into recurrent networks. The neurons are provided with an enriched functionality in order to accommodate a fuzzy representation of FFA states. This enriched neuron functionality also permits fuzzy parameters of FFA to be directly represented as parameters of the neural network. We also prove the stability of fuzzy finite state dynamics of the constructed neural networks for finite values of network weight and, through simulations, give empirical validation of the proofs. Hence, we prove various knowledge equivalence representations between neural and fuzzy systems and models of automata.
|
3051
|
Neural Networks for Pattern Recognition
– Bishop
- 1995
|
|
2771
|
Introduction to Automata Theory, Language, and Computation
– Hopcroft, Ullman
- 1979
|
|
1871
|
Neural networks: A Comprehensive Foundation
– Haykin
- 1994
|
|
1486
|
Fuzzy sets
– Zadeh
- 1965
|
|
1092
|
Finding structure in time
– Elman
- 1990
|
|
465
|
Nonlinear Systems
– Khalil
- 1996
|
|
445
|
Analog VLSI and Neural Systems
– Mead
- 1989
|
|
303
|
Prade, Fuzzy Sets & Systems : Theory and Applications
– Dubois
- 1990
|
|
278
|
Fuzzy Logic in Control Systems: Fuzzy Logic Controller-Part I
– Lee
- 1990
|
|
258
|
Representation of events in nerve nets and finite automata
– Kleene
- 1956
|
|
193
|
The induction of dynamical recognizers
– Pollack
- 1991
|
|
173
|
Learning and extracting finite state automata with second-order-recurrent neural networks
– Giles, Miller, et al.
- 1992
|
|
152
|
On the computational power of neural nets
– Siegelmann, Sontag
- 1995
|
|
138
|
Finite state automata and simple recurrent networks
– Cleeremans, Servan-Schreiber, et al.
- 1989
|
|
102
|
The dynamics of discrete-time computation, with application to recurrent neural networks and �nite state machine extraction
– Casey
- 1996
|
|
94
|
Neural Networks and Analog Computation: Beyond the Turing Limit. Birkhäuser
– Siegelmann
- 1999
|
|
91
|
Induction of finite-state languages using second-order recurrent networks
– Watrous, Kuhn
- 1992
|
|
67
|
Constructing deterministic finite-state automata in recurrent neural networks
– Omlin, Giles
- 1996
|
|
64
|
Extraction of rules from discrete-time recurrent neural networks. Neural Networks
– Omlin, Giles
- 1996
|
|
51
|
Learning finite state machines with self-clustering recurrent networks
– Zeng, Goodman, et al.
- 1993
|
|
49
|
Logic Synthesis
– Devadas, Ghosh, et al.
- 1994
|
|
38
|
Representation of finite state automata in recurrent radial basis function networks
– Frasconi, Gori, et al.
- 1996
|
|
34
|
Extraction, insertion and refinement of symbolic rules in dynamically driven recurrent neural networks
– Giles, Omlin
- 1993
|
|
33
|
Using knowledgebased neural network to improve algorithms: refining the Chou-Fasman algorithm for protein folding. Machine Learning 11
– Maclin, Shavlik
- 1993
|
|
32
|
Learning, action and consciousness: A hybrid approach toward modelling consciousness
– Sun
- 1997
|
|
26
|
Neural networks in computer intelligence
– Fu
- 1994
|
|
25
|
Rule revision with recurrent neural networks
– Omlin, Giles
- 1996
|
|
22
|
Stable encoding of large finite-state automata in recurrent neural networks with sigmoid discriminants
– Omlin, Giles
- 1996
|
|
20
|
A fuzzy logic controller for a traffic junction
– Pappis, Mamdani
- 1977
|
|
17
|
Developing hybrid symbolic/connectionist models
– Hendler
- 1991
|
|
13
|
Maximin automata
– Santos
- 1968
|
|
13
|
Fuzzy Finite-State Automata Can Be Deterministically Encoded into Recurrent Neural Networks
– Omlin, Thornber, et al.
- 1998
|
|
13
|
Neural information processing and VLSI
– Sheu, Choi
- 1995
|
|
11
|
Fuzzy languages and their relation to human and machine intelligence
– Zadeh
- 1971
|
|
11
|
Deterministic acceptors of regular fuzzy languages
– Thomason, Marinos
- 1974
|
|
10
|
Industrial applications of fuzzy logic at General Electric
– Bonissone, Badami, et al.
- 1995
|
|
10
|
Fuzzy logic for control of roll and moment for a flexible wing aircraft
– Chiu, Chand, et al.
- 1991
|
|
10
|
The logic of automata
– Gaines, Kohout
- 1976
|
|
10
|
Synthesis and analysis of fuzzy logic finite state machine models
– Grantner, Patyra
- 1994
|
|
10
|
Recurrent fuzzy logic using neural networks
– Khan, Unal
- 1995
|
|
9
|
FASY: A fuzzy-logic based tool for analog synthesis
– Torralba, Franquelo
- 1996
|
|
9
|
Fuzzy specification of finite state machines
– Mensch, Lipp
- 1990
|
|
8
|
Nauta Lemke, "Application of a fuzzy controller in a warm water plant
– Kickert, van
- 1976
|
|
8
|
A fuzzy finite state machine implementation based on a neural fuzzy system
– Unal, Khan
- 1994
|
|
7
|
A hybrid fuzzy-neural expert system for diagnosis
– Herrmann
- 1995
|
|
7
|
A fuzzy logic-based financial transaction system
– Corbin
- 1994
|
|
6
|
Learning and fine tuning fuzzy logic controllers through reinforcement
– Berenji, Khedkar
- 1992
|
|
6
|
Multi-objective decision-making under uncertainty fuzzy logic methods
– Hardy
- 1994
|
|
6
|
Design for machining using expert system and fuzzy logic approach
– Yang, Kalambur
- 1995
|
|
6
|
VLSI implementations of fuzzy logic finite state machines
– Grantner, Patyra
- 1993
|
|
