Grammatical rules for the automated construction of heuristics
18 Jul 2010-pp 1-8
TL;DR: This paper presents a three-steps methodology that combines multiple sequence alignment and grammatical induction in order to automatically generate high performing solving strategies for a combinatorial optimisation problem.
Abstract: Developing a problem-domain independent methodology to automatically generate high performing solving strategies for specific problems is one of the challenging trends on hyper-heuristics design. Designing hyper-heuristics is important because they raise the level of generality on automated problem solving by attempting to select and/or generate tailored heuristics for the problem at hand. In this paper, we present a three-steps methodology that combines multiple sequence alignment and grammatical induction in order to automatically generate high performing solving strategies for a combinatorial optimisation problem. We present proof-of-concept results of applying this methodology to instances of the well-known symmetric TSP. The goal here is to demonstrate feasibility rather than compete with state of the art TSP solvers. This TSP is chosen only because it is an easy to state and well known problem.
Citations
More filters
01 Jan 2005
TL;DR: Several variants and generalizations of the Or-opt heuristic for the Symmetric Travelling Salesman Problem are developed and compared on random and planar instances to significantly improve upon the standard 2-opt and Or- opt heuristics.
Abstract: Several variants and generalizations of the Or-opt heuristic for the Symmetric Travelling Salesman Problem are developed and compared on random and planar instances. Some of the proposed algorithms are shown to significantly improve upon the standard 2-opt and Or-opt heuristics.
11 citations
References
More filters
08 Dec 2003
TL;DR: The results of the experiments show that simple hyperheuristic approaches can successfully tackle a complex real-world problem provided that low level heuristics are carefully selected to treat various constraints.
Abstract: We investigate the performance of several hyperheuristics applied to a real-world personnel-scheduling problem. A hyperheuristic is a high-level search method which manages the choice of low level heuristics, making it a robust and easy to implement approach for complex real-world problems. We need only to develop new low level heuristics and objective functions to apply a hyperheuristic to an entirely new problem. Although hyperheuristic methods require limited problem-specific information, their performance for a particular problem is determined to a great extent by the quality of low level heuristics used. We address the question of designing the set of low level heuristics for the problem under consideration. We construct a large set of low level heuristics by using a technique which allows us to "multiply" partial low level heuristics. We apply hyperheuristic methods to a trainer scheduling problem using commercial data from a large financial institution. The results of the experiments show that simple hyperheuristic approaches can successfully tackle a complex real-world problem provided that low level heuristics are carefully selected to treat various constraints. We also examine how the choice of different sets of low level heuristics affects solution quality.
62 citations
"Grammatical rules for the automated..." refers background in this paper
...…of Computer Science, University of Nottingham, UK, email:gzt@cs.nott.ac.uk Natalio Krasnogor, ASAP Group, School of Computer Science, University of Nottingham, UK, email:nxk@cs.nott.ac.uk presented and discussed in Section V. Finally, conclusions and further work are the subject of Section VI....
[...]
TL;DR: Several variants and generalizations of the Or-opt heuristic for the Symmetric Travelling Salesman Problem are developed and compared on random and planar instances as mentioned in this paper, and some of the proposed algorithms are shown to significantly improve upon the standard 2-opt and Or-Opt heuristics.
Abstract: Several variants and generalizations of the Or-opt heuristic for the Symmetric Travelling Salesman Problem are developed and compared on random and planar instances. Some of the proposed algorithms are shown to significantly improve upon the standard 2-opt and Or-opt heuristics.
35 citations
Proceedings Article•
09 Dec 2003TL;DR: A pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of linguistic structures from a plain natural-language corpus, achieving a level of performance considered to be "intermediate" for 9th-grade students, despite having been trained on a corpus containing transcribed speech of parents directed to small children.
Abstract: We describe a pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of linguistic structures from a plain natural-language corpus. This paper addresses the issues of learning structured knowledge from a large-scale natural language data set, and of generalization to unseen text. The implemented algorithm represents sentences as paths on a graph whose vertices are words (or parts of words). Significant patterns, determined by recursive context-sensitive statistical inference, form new vertices. Linguistic constructions are represented by trees composed of significant patterns and their associated equivalence classes. An input module allows the algorithm to be subjected to a standard test of English as a Second Language (ESL) proficiency. The results are encouraging: the model attains a level of performance considered to be "intermediate" for 9th-grade students, despite having been trained on a corpus (CHILDES) containing transcribed speech of parents directed to small children.
30 citations
"Grammatical rules for the automated..." refers background in this paper
...In the second case, the focus is on searching components that once combined generate a new heuristic suitable for the problem at hand....
[...]
TL;DR: It is pointed out in this paper that memetic algorithms for graph partitioning and maximum network flow (both with important practical applications) also give rise to PLS-complete problems.
Abstract: In previous work (Krasnogor, http://www.cs.nott.ac.uk/~nxk/papers.html. In: Studies on the Theory and Design Space of Memetic Algorithms. Ph.D. thesis, University of the West of England, Bristol, UK, 2002; Krasnogor and Smith, IEEE Trans Evol Algorithms 9(6):474–488, 2005) we develop a syntax-only classification of evolutionary algorithms, in particular so-called memetic algorithms (MAs). When “syntactic sugar” is added to our model, we are able to investigate the polynomial local search (PLS) complexity of memetic algorithms. In this paper we show the PLS-completeness of whole classes of problems that occur when memetic algorithms are applied to the travelling salesman problem using a range of mutation, crossover and local search operators. Our PLS-completeness results shed light on the worst case behaviour that can be expected of a memetic algorithm under these circumstances. Moreover, we point out in this paper that memetic algorithms for graph partitioning and maximum network flow (both with important practical applications) also give rise to PLS-complete problems.
29 citations
"Grammatical rules for the automated..." refers methods in this paper
...In the pattern-based heuristics generation, an input dataset is employed to train randomly generated sequences of low-level heuristics (high-level heuristics)....
[...]
25 Jun 2007
TL;DR: It is shown that using neither POS-tags induced from Biemann's unsupervised POS-tagging algorithm nor hand-corrected POS- tags as input improves this situation, and it is argued for the development of entirely incremental grammar induction algorithms.
Abstract: I review a number of grammar induction algorithms (ABL, Emile, Adios), and test them on the Eindhoven corpus, resulting in disappointing results, compared to the usually tested corpora (ATIS, OVIS). Also, I show that using neither POS-tags induced from Biemann's unsupervised POS-tagging algorithm nor hand-corrected POS-tags as input improves this situation. Last, I argue for the development of entirely incremental grammar induction algorithms instead of the approaches of the systems discussed before.
28 citations
"Grammatical rules for the automated..." refers background in this paper
...During the fabrication process, hyper-heuristics receive feedback from the problem domain which indicates how good are the chosen heuristics for solving the problem at hand, hence driving the search process....
[...]