Learning DFA: evolution versus evidence driven state merging

Lucas, Simon M.; Reynolds, T.J.

doi:10.1109/cec.2003.1299597

Cited by 35 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal is to find the permutation p that maximises q(p) In this example, this is the original alignment p = (0, 2, 4, 1, 3), giving the following sum: q(p) = i s ip(i) = 45 + 29 + 23 + 9 + 0 = 106 (14) Applying this in the appropriate way leads to an optimal alignment between c and c . Note however that this is not always the case i.e.…”

Section: A Worked Examplementioning

confidence: 98%

See 1 more Smart Citation

A statistically aligned recombination operator for finite state machines

Lucas

2007

2007 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

Learning finite state machines from samples of data has been extensively studied within machine learning and since the dawn of evolutionary computation.Conventional crossover or recombination operators used for finite state machines suffer from the competing conventions problem, caused by the combinatorial number of isomorphisms of each distinct machine. This paper introduces an efficient alignment operator to counteract this phenomenon. Results show that when in the neighbourhood of the target machine, the aligned crossover operator reaches the optimum in far few steps (on average) than either a naive crossover operator or a standard flip-style mutation operator.

show abstract

Section: A Worked Examplementioning

confidence: 98%

“…Evolutionary approaches have been investigated by Dupont [12], Luke et al [13], and Lucas and Reynolds [14]. For a comprehensive survey of the field see Cicchello and Kramer [15].…”

Section: Introductionmentioning

confidence: 99%

A statistically aligned recombination operator for finite state machines

Lucas

2007

2007 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Second, we are interested in exploring techniques to increase the readability of our generated diagrams, either through additional tasks or post-processing. Additionally, we are investigating the potential of leveraging synthesis (e.g., [8][9][10][11][12][13][13][14][15]) and/or machine learning (e.g., [34][35][36]) approaches to generate an initial behavioral model that is then manipulated by the AVIDA organisms to create potentially more robust and resilient compliant behavioral models. This combination of techniques had the potential to improve the performance of AVIDA, but may also limit the exploration of the solution space.…”

Section: Scalabilitymentioning

confidence: 99%

Digital Evolution of Behavioral Models for Autonomic Systems

Goldsby

Cheng

McKinley

et al. 2008

2008 International Conference on Autonomic Computing

View full text Add to dashboard Cite

We describe an automated method to generating models of an autonomic system. Specifically, we generate UML state diagrams for a set of interacting objects, including the extension of existing state diagrams to support new behavior. The approach is based on digital evolution, a form of evolutionary computation that enables a designer to explore an enormous solution space for complex problems. In our application of this technology, an evolving population of digital organisms is subjected to natural selection, where organisms are rewarded for generating state diagrams that support key scenarios and satisfy critical properties as specified by the developer. To achieve this capability, we extended the AVIDA digital evolution platform to enable state diagram generation, and integrated AVIDA with third-party software engineering tools, e.g., the Spin model checker, to assess the generated state diagrams. To illustrate this approach, we successfully applied it to the generation of state diagrams describing the autonomous navigation behavior of a humanoid robot.

show abstract

“…Grammar induction is an attempt to model the internal structure of the hidden FSM, based only on pairs of sentences and classifications. The most successful grammar induction algorithms produced so far are heuristic in nature (see [14] for an overview), and there have been several attempts to evolve FSMs from sample data [25], [45], [46], but all approaches so far assume that a representative sample of sentences have already been classified by the target FSM. In other words they follow the batch-oriented approach to system identification [see Fig.…”

Section: Application 1: Grammar Inductionmentioning

confidence: 99%

Nonlinear System Identification Using Coevolution of Models and Tests

Bongard

Lipson

2005

IEEE Trans. Evol. Computat.

110

View full text Add to dashboard Cite

We present a coevolutionary algorithm for inferring the topology and parameters of a wide range of hidden nonlinear systems with a minimum of experimentation on the target system. The algorithm synthesizes an explicit model directly from the observed data produced by intelligently generated tests. The algorithm is composed of two coevolving populations. One population evolves candidate models that estimate the structure of the hidden system. The second population evolves informative tests that either extract new information from the hidden system or elicit desirable behavior from it. The fitness of candidate models is their ability to explain behavior of the target system observed in response to all tests carried out so far; the fitness of candidate tests is their ability to make the models disagree in their predictions. We demonstrate the generality of this estimation-exploration algorithm by applying it to four different problems-grammar induction, gene network inference, evolutionary robotics, and robot damage recovery-and discuss how it overcomes several of the pathologies commonly found in other coevolutionary algorithms. We show that the algorithm is able to successfully infer and/or manipulate highly nonlinear hidden systems using very few tests, and that the benefit of this approach increases as the hidden systems possess more degrees of freedom, or become more biased or unobservable. The algorithm provides a systematic method for posing synthesis or analysis tasks to a coevolutionary system.

show abstract

Learning DFA: evolution versus evidence driven state merging

Cited by 35 publications

References 12 publications

A statistically aligned recombination operator for finite state machines

A statistically aligned recombination operator for finite state machines

Digital Evolution of Behavioral Models for Autonomic Systems

Nonlinear System Identification Using Coevolution of Models and Tests

Contact Info

Product

Resources

About