A Hyper-Heuristic Framework with XCS: Learning to Create Novel Problem-Solving Algorithms Constructed from Simpler Algorithmic Ingredients

Marín-Blázquez, Javier G.; Schulenburg, Sonia

doi:10.1007/978-3-540-71231-2_14

Cited by 13 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the hyper-heuristic research aims at solving typical optimisation problems, such as production scheduling [15,37], educational timetabling [26], 1D packing [24], 2D cutting and packing [18], constraint satisfaction [36], and vehicle routing [19]. Applications of hyper-heuristics to machine learning are not so frequent and much more recent than optimisation applications.…”

Section: Background On Hyper-heuristicsmentioning

confidence: 99%

Investigating fitness functions for a hyper-heuristic evolutionary algorithm in the context of balanced and imbalanced data classification

Barros

Basgalupp

Carvalho

2014

Genet Program Evolvable Mach

View full text Add to dashboard Cite

In this paper, we analyse in detail the impact of different strategies to be used as fitness function during the evolutionary cycle of a hyper-heuristic evolutionary algorithm that automatically designs decision-tree induction algorithms (HEAD-DT). We divide the experimental scheme into two distinct scenarios:(1) evolving a decision-tree induction algorithm from multiple balanced data sets; and (2) evolving a decision-tree induction algorithm from multiple imbalanced data sets. In each of these scenarios, we analyse the difference in performance of wellknown classification performance measures such as accuracy, F-Measure, AUC, recall, and also a lesser-known criterion, namely the relative accuracy improvement. In addition, we analyse different schemes of aggregation, such as simple average, median, and harmonic mean. Finally, we verify whether the best-performing fitness functions are capable of providing HEAD-DT with algorithms more effective than traditional decision-tree induction algorithms like C4.5, CART, and REPTree. Experimental results indicate that HEAD-DT is a good option for generating algorithms tailored to (im)balanced data, since it outperforms state-of-the-art decision-tree induction algorithms with statistical significance.

show abstract

Section: Background On Hyper-heuristicsmentioning

confidence: 99%

Investigating fitness functions for a hyper-heuristic evolutionary algorithm in the context of balanced and imbalanced data classification

Barros

Basgalupp

Carvalho

2014

Genet Program Evolvable Mach

View full text Add to dashboard Cite

show abstract

“…XCS, the extended classifier system (Wilson 1995), avoids that trap by focusing more on the prediction accuracy of a rule than on the number of test cases it covered, and has been extremely successful in areas such as data mining. See also Marin-Blazquez and Schulenburg (2007).…”

Section: Remarksmentioning

confidence: 99%

Hyper-heuristics

Ross¹

2013

Search Methodologies

View full text Add to dashboard Cite

“…Offline learning seeks to extract information obtained from a set of training instances in order to better inform the subsequent search process. Examples of offline learning for hyper-heuristics includes learning-classifier systems [17], case-based reasoning [18] and genetic programming [19]. While much work has been done in the offline analysis of landscapes and devising metrics of landscape quality ( [20], [21], [22], [23], [24], [25]), this information is not routinely used to inform online activity.…”

Section: Learningmentioning

confidence: 99%

Searching the Hyper-heuristic Design Space

et al. 2013

View full text Add to dashboard Cite

Abstract. We extend a previous mathematical formulation of hyperheuristics to reflect the emerging generalization of the concept. We show that this leads naturally to a recursive definition of hyper-heuristics and to a division of responsibility that is suggestive of a blackboard architecture, in which individual heuristics annotate a shared workspace with information that may also be exploited by other heuristics. Such a framework invites consideration of the kind of relaxations of the domain barrier that can be achieved without loss of generality. We give a concrete example of this architecture with an application to the 3-SAT domain that significantly improves on a related token-ring hyper-heuristic.

show abstract

A Hyper-Heuristic Framework with XCS: Learning to Create Novel Problem-Solving Algorithms Constructed from Simpler Algorithmic Ingredients

Cited by 13 publications

References 9 publications

Investigating fitness functions for a hyper-heuristic evolutionary algorithm in the context of balanced and imbalanced data classification

Investigating fitness functions for a hyper-heuristic evolutionary algorithm in the context of balanced and imbalanced data classification

Hyper-heuristics

Searching the Hyper-heuristic Design Space

Contact Info

Product

Resources

About