Genetics-based learning of new heuristics: rational scheduling of experiments and generalization

Wah, Benjamin W.; Ieumwananonthachai, Arthur; Chu, Lon-Chan; Aizawa, Akiko

doi:10.1109/69.469821

Cited by 20 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This study is unique in the literature, as the automated approach is compared against those produced by three NASA programmers, producing competitive results, and even often outperforming the human programmers. Another interesting learning approach in the mid-1990s was termed 'Teacher' (Wah et al, 1995;Wah and Ieumwananonthachai, 1999) (an acronym for TEchniques for the Automated Creation of HEuRistics), which was designed as a system for learning and generalising heuristics used in problem solving. The objective was to find improved heuristic methods as compared with existing ones, in applications with little or non-existent domain knowledge.…”

Section: Automated Learning Of Heuristic Methodsmentioning

confidence: 99%

Hyper-heuristics: a survey of the state of the art

Burke

Gendreau

Hyde

et al. 2013

Journal of the Operational Research Society

970

550

View full text Add to dashboard Cite

Hyper-heuristics comprise a set of approaches that are motivated (at least in part) by the goal of automating the design of heuristic methods to solve hard computational search problems. An underlying strategic research challenge is to develop more generally applicable search methodologies. The term hyper-heuristic is relatively new; it was first used in 2000 to describe heuristics to choose heuristics in the context of combinatorial optimisation. However, the idea of automating the design of heuristics is not new; it can be traced back to the 1960s. The definition of hyper-heuristics has been recently extended to refer to a search method or learning mechanism for selecting or generating heuristics to solve computational search problems. Two main hyper-heuristic categories can be considered: heuristic selection and heuristic generation. The distinguishing feature of hyper-heuristics is that they operate on a search space of heuristics (or heuristic components) rather than directly on the search space of solutions to the underlying problem that is being addressed. This paper presents a critical discussion of the scientific literature on hyper-heuristics including their origin and intellectual roots, a detailed account of the main types of approaches, and an overview of some related areas. Current research trends and directions for future research are also discussed.

show abstract

Section: Automated Learning Of Heuristic Methodsmentioning

confidence: 99%

Hyper-heuristics: a survey of the state of the art

Burke

Gendreau

Hyde

et al. 2013

Journal of the Operational Research Society

970

550

View full text Add to dashboard Cite

show abstract

“…Because there were several possible heuristics to use in each case, the system used a simple hill-climbing approach to investigate combinations of them, testing each on 50 different problems, and was able to discover an effective combination. Wah et al (1995) developed an early heuristics-learning system named Teacher and discussed a number of the issues raised in this chapter.…”

Section: A Little Historymentioning

confidence: 99%

Hyper-heuristics

Ross¹

2013

Search Methodologies

View full text Add to dashboard Cite

“…Artificial intelligence research groups have been working towards the study and the proposal of adequate models and computational hybrid architectures for creative reasoning by empowering cross-contributions from CBR and evolutionary computation (EC) (Koza, 2000). Teacher (Techniques for the Automated Creation of HEuRestics) is a system for learning and for generalizing heuristics used in problem solving (Wah, Ieumwananonthachai, Chu, & Aizawa, 1995) that learns knowledge-lean heuristics with statistically measured performance. The integration of concepts of neurofuzzy computing and CBR can potentially lead to efficient decision support systems.…”

Section: State Of the Artmentioning

confidence: 99%