Rule Induction by Estimation of Distribution Algorithms

Sierra, Basilio; Jiménez, Estefanía Álvarez; Inza, Iñaki; Larrañaga, Pedro; Muruzábal, Jorge

doi:10.1007/978-1-4615-1539-5_15

Cited by 4 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table I shows a summary of the papers reviewed in this section. Pittsburgh approach [122] UMDA, COMIT, EBNA Pittsburgh approach [123], [124] BOA Fuzzy rule-based systems [125] UMDA, MIMIC, UMDA G c Support vector machines Hyperparameters [127] UMDA G c , BUMDA Artificial neural networks Weights of a multilayer perceptron [129] PBIL Weights of a multilayer perceptron [130] PBIL Weights of a multilayer perceptron [131] UMDA…”

Section: Edas In Supervised Learningmentioning

confidence: 99%

“…In [122], an EDA for rule induction that can be seen as an instantiation of the Pittsburgh approach was proposed. The individual representation of the IF part of the rule (the antecedent) consists of the disjunction of simple antecedents (the optimization variables), each with a dimension given by n, allowing each variable to take values that are "equal to", "different from", and "any possible value".…”

Section: Edas In Supervised Learningmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Distribution Algorithms in Machine Learning: A Survey

Larrañaga,

Bielza

2024

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

The automatic induction of machine learning models capable of addressing supervised learning, feature selection, clustering and reinforcement learning problems requires sophisticated intelligent search procedures. These searches are usually performed in the possible model structure spaces, leading to combinatorial optimization problems, and in the parameter spaces, where it is necessary to solve continuous optimization problems. This paper reviews how the estimation of distribution algorithms, a kind of evolutionary algorithm, can be used to address these problems. Topics include preprocessing, mining association rules, selecting variables, searching for the optimal supervised learning model (both probabilistic and nonprobabilistic models), finding the best hierarchical, partitional or probabilistic clustering, obtaining the optimal policy in reinforcement learning and performing inference and structural learning in Bayesian networks for association discovery. Interesting guidelines for future work in this area are also provided.

show abstract

Section: Edas In Supervised Learningmentioning

confidence: 99%

Section: Edas In Supervised Learningmentioning

confidence: 99%

Estimation of Distribution Algorithms in Machine Learning: A Survey

Larrañaga,

Bielza

2024

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

show abstract

“…EDA guide the search by explicitly building the probabilistic model of promising candidate solutions. The detail discussion on EDA is beyond the scope of this paper, but interested reader can refer to papers by Ceberio et al [14], Shirazi et al [15], Shakya and Santana [16], Simon [17] and Pelikan [18]. In the area of Search-Based Software Engineering (SBSE), to the best of our knowledge, no attempt has been made to employ any variant of high-order EDA (which includes bivariate or multivariate statistics) in SPL testing.…”

Section: Related Workmentioning

confidence: 99%

“…This dependency would suggest that the two features should be paired, and those that have strong dependency should be considered first. A variant of EDA that has the capability to find this dependency is called the Bivariate Marginal Distribution Algorithm (BMDA) [17], [28]. It uses a factorization of the univariate marginal and joint probability distribution that able to expose second-order dependencies.…”

Section: B Bivariate Distribution Of Spl Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Marginal Distribution Algorithm for Feature Model Test Configuration Generation

Sahid,

Saringat,

Hamzah

et al. 2023

IJACSA

View full text Add to dashboard Cite

Generating test configuration for Software Product Line (SPL) is difficult, due to the exponential effect of feature combination. Pairwise testing can generate test input for a single software product that deviates from exhaustive testing, nevertheless proven to be effective. In the context of SPL testing, to generate minimal test configuration that maximizes pairwise coverage is not trivial, especially when dealing with a huge number of features and when constraints must be satisfied, which is the case in most SPL systems. In this paper, we propose an estimation of distribution algorithm, based on pairwise testing, to alleviate this problem. Comparisons are made against a greedybased and a constraint handling based approach. The experiments demonstrate the feasibility of the proposed algorithm, such that it achieves better test configurations dissimilarity and at the same time maintain the test configuration size and pairwise coverage. This is supported by analysis using descriptive statistics.

show abstract

An Estimation of Distribution Algorithm for Part Cell Formation Problem

Ibrahim

Jarboui

Rebaï

Industrial Engineering

View full text Add to dashboard Cite

The aim of this chapter is to propose a new heuristic for Machine Part Cell Formation problem. The Machine Part Cell Formation problem is the important step in the design of a Cellular Manufacturing system. The objective is to identify part families and machine groups and consequently to form manufacturing cells with respect to minimizing the number of exceptional elements and maximizing the grouping efficacy. The proposed algorithm is based on a hybrid algorithm that combines a Variable Neighborhood Search heuristic with the Estimation of Distribution Algorithm. Computational results are presented and show that this approach is competitive and even outperforms existing solution procedures proposed in the literature.

show abstract

Rule Induction by Estimation of Distribution Algorithms

Cited by 4 publications

References 5 publications

Estimation of Distribution Algorithms in Machine Learning: A Survey

Estimation of Distribution Algorithms in Machine Learning: A Survey

Marginal Distribution Algorithm for Feature Model Test Configuration Generation

An Estimation of Distribution Algorithm for Part Cell Formation Problem

Contact Info

Product

Resources

About