Results 1 
6 of
6
Learning Evaluation Functions to Improve Optimization by Local Search
 Journal of Machine Learning Research
, 2000
"... This paper describes algorithms that learn to improve search performance on largescale optimization tasks. The main algorithm, Stage, works by learning an evaluation function that predicts the outcome of a local search algorithm, such as hillclimbing or Walksat, from features of states visited durin ..."
Abstract

Cited by 57 (0 self)
 Add to MetaCart
This paper describes algorithms that learn to improve search performance on largescale optimization tasks. The main algorithm, Stage, works by learning an evaluation function that predicts the outcome of a local search algorithm, such as hillclimbing or Walksat, from features of states visited during search. The learned evaluation function is then used to bias future search trajectories toward better optima on the same problem. Another algorithm, XStage, transfers previously learned evaluation functions to new, similar optimization problems. Empirical results are provided on seven largescale optimization domains: binpacking, channel routing, Bayesian network structurefinding, radiotherapy treatment planning, cartogram design, Boolean satisfiability, and Boggle board setup.
Graphbased evolutionary algorithms
 IEEE Trans. Evolut. Comput. Algor
, 2006
"... Abstract—Evolutionary algorithms use crossover to combine information from pairs of solutions and use selection to retain the best solutions. Ideally, crossover takes distinct good features from each of the two structures involved. This process creates a conflict: progress results from crossing ove ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
Abstract—Evolutionary algorithms use crossover to combine information from pairs of solutions and use selection to retain the best solutions. Ideally, crossover takes distinct good features from each of the two structures involved. This process creates a conflict: progress results from crossing over structures with different features, but crossover produces new structures that are like their parents and so reduces the diversity on which it depends. As evolution continues, the algorithm searches a smaller and smaller portion of the search space. Mutation can help maintain diversity but is not a panacea for diversity loss. This paper explores evolutionary algorithms that use combinatorial graphs to limit possible crossover partners. These graphs limit the speed and manner in which information can spread giving competing solutions time to mature. This use of graphs is a computationally inexpensive method of picking a global level of tradeoff between exploration and exploitation. The
Abstract An Application of Graph Based Evolutionary Algorithms for Diversity Preservation
"... A difficult application case of evolutionary algorithms is that in which individual fitness evaluations take several processorminutes to a few processorhours. The design of evolutionary algorithms with such expensive fitness evaluation differs substantially from the norm where fitness evaluation i ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
A difficult application case of evolutionary algorithms is that in which individual fitness evaluations take several processorminutes to a few processorhours. The design of evolutionary algorithms with such expensive fitness evaluation differs substantially from the norm where fitness evaluation is rapid. In this paper we apply evolutionary algorithms to a thermal systems engineering design problem the design of a biomass cook stove currently in use in Central America. Fitness evaluation involves the use of computational fluid dynamics(CFD) modeling of the flow of hot air and heat transport within the stove to equalize the surface temperature. The goal is to optimizes the placement and size of baffles that deflect hot gasses underneath the cook top of the stove. Three techniques are used to permit an evolutionary algorithm to function on this challenging problem using a population of relatively small size. First, computations are performed on a Linux cluster machine yielding a large, fixed performance increase. Second, the resolution of the mesh for CFD computations used a minimal mesh that yields acceptable fidelity of CFD computations. Third, a diversity preserving technique called a graph based evolutionary algorithm(GBEA) is used to retain population diversity during evolution. A usable stove design, subsequently deployed in the field, was located by the evolutionary algorithm. In this paper we demonstrate that GBEAs preserve diversity on this baffle design problem and give evidence that highly connected graphs are a good choice for future work on analogous CFD problems. Diversity preservation is a function of both tournament size and the connectivity (geography) of the graph used. I.
Learning Classifier Systems with Neural Network Representation
, 2006
"... There are many people I would like to thank for their support. Principally I thank my family, Sue, Nick, Katie and William, and my Supervisor Larry Bull. All have shown tolerance, forbearance, support and inspiration well beyond the call of duty. In addition Dave Wyatt and Praminda CalebSolly have ..."
Abstract
 Add to MetaCart
(Show Context)
There are many people I would like to thank for their support. Principally I thank my family, Sue, Nick, Katie and William, and my Supervisor Larry Bull. All have shown tolerance, forbearance, support and inspiration well beyond the call of duty. In addition Dave Wyatt and Praminda CalebSolly have been very knowledgeable, approachable and helpful, I owe them a lot. The UWE LCSG has been a key source of ideas, knowledge and inspiration. Books and papers cannot provide such a level of understanding and debate about fundamental issues. Amongst the key players Larry Bull, Alwyn Barry, Dave Wyatt, Matt Studley, Chris Stone, Tony Pipe, Brian Carse and Rob Smith have always provided difficult and thought provoking questions, and sometimes even answers. Lastly thanks to Paul Lewis, Joe Mackenzie both of BT, Terry Fogarty, and Roger Miles who in there own ways facilitated the move from being a competent project manager to entering the (from Huxley) “brave new world that hath such people in’t ” of evolutionary and neural computing. This thesis investigates a hybrid of evolutionary computing and neural computing which long has been a goal of machine learning. XNCS is a neural and hence a more complex version of XCS (Wilson 1995), the preeminent accuracy based Learning Classifier System (LCS) (Holland, 1986). XCS differs from other
Graph Based Genetic Algorithms Mark Smucker Firefly Network
"... Abstract Genetic algorithms use crossover to blend pairs of putative solutions to a problem in hopes of creating novel solutions. At its best, crossover takes distinct good features from each of the two structures involved in the crossover. This creates a conflict: progress results from crossing ov ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract Genetic algorithms use crossover to blend pairs of putative solutions to a problem in hopes of creating novel solutions. At its best, crossover takes distinct good features from each of the two structures involved in the crossover. This creates a conflict: progress results from crossing over distinct types of structures but such crossover produces new structures that are like their parents, reducing the diversity on which successful crossover depends. In this paper we describe and test genetic algorithms that use a combinatorial graph to limit choice of crossover partner. This gives a computationally cheap method of picking a level of tradeoff between having heterogeneous crossover (crossover between genetically distinct individuals) and preservation of population diversity. Statistics for estimating the degree to which a given graphical population structure favors population diversity or heterogeneous crossover are given. These statistics are computed for ten example graphs. These graphs are then used as population structures for genetic algorithms of three test problems: a trivial string evolver, the plusonerecallstore (PORS) test suite for genetic programming [3, 4], and simple string controllers for Astro Teller’s Tartarus problem. [13] 1
Learning Evaluation Functions to Improve Local Search
"... This paper describes Stage, a learning algorithm that automatically improves search performance on largescale optimization problems. Stage learns an evaluation function that predicts the outcome of a local search algorithm, such as hillclimbing or Walksat, from features of states visited during sea ..."
Abstract
 Add to MetaCart
This paper describes Stage, a learning algorithm that automatically improves search performance on largescale optimization problems. Stage learns an evaluation function that predicts the outcome of a local search algorithm, such as hillclimbing or Walksat, from features of states visited during search. The learned evaluation function is used to bias future search trajectories toward better optima on the same problem. This paper presents the Stage algorithm; an extension, XStage, that transfers learned evaluation functions to new, similar optimization problems; and empirical results on seven largescale optimization domains: binpacking, channel routing, Bayes network structurefinding, radiotherapy treatment planning, cartogram design, Boolean satisfiability, and Boggle board setup.