Linkage Learning, Overlapping Building Blocks, and a Systematic Strategy for Scalable Recombination
Yu, T.-L., Sastry, K., Goldberg, D.E. (2005)TR No.: 2005016 | Download PDF | Download PS
Abstract:
This paper aims at an important, but poorly studied area in genetic algorithm (GA) field: How to design the crossover
operator for problems with overlapping building blocks (BBs). To investigate this issue systematically, the relationship between an inaccurate linkage model and the convergence time of GA is studied. Specifically, the effect of the error of […]
Posted: March 20th, 2005 under Genetic algorithms. Comments: none
Simple Models of Hierarchical Organizations
Yassine, A., Goldberg, D.E., Yu, T.-L. (2005)TR No.: 2005015 | Download PDF | Download PS
Abstract:
This paper develops analytical models for analyzing hierarchical organizations, through the creation and use of little models of organizational interaction to balance the communication time within and between organizational hierarchies. Then it examines these theoretical models on the basis of a data set of 678 school systems in Texas. Analysis of the dataset suggests that, […]
Posted: March 16th, 2005 under Genetic algorithms. Comments: none
An Information Theoretic Method for Developing Modular Architectures Using Genetic Algorithms
Yu, T.-L., Yassine, A., Goldberg, D.E. (2005)TR No.: 2005014 | Download PDF | Download PS
Abstract:
Designing modular products can result in many benefits to both manufacturers and consumers. The development of modular products requires the identification of highly interactive groups of elements and arranging (i.e., clustering) them into modules. However, no rigorous clustering technique can be found in engineering design literature. This paper uses the design structure […]
Posted: March 12th, 2005 under Genetic algorithms. Comments: none
Military Antenna Design Using Simple and Competent Genetic Algorithms
Santarelli S., Yu, T.-L., Goldberg D. E., Altshuler E., O’Donnell T., Southall H., Mailloux R. (2005)TR No.: 2005013 | Download PDF | Download PS
Abstract:
Over the past decade, the Air Force Research Laboratory (AFRL) Antenna Technology Branch at Hanscom AFB has employed the simple genetic algorithm (SGA) as an optimization tool for a wide variety of antenna applications. Over roughly the same period, researchers at the Illinois Genetic Algorithm Laboratory (IlliGAL) at the University of Illinois at Urbana […]
Posted: March 8th, 2005 under Genetic algorithms. Comments: none
Generalization in the XCSF Classifier System: Analysis, Improvement, and Extension
Lanzi P.L., Loiacono D., Wilson S.W., Goldberg D.E. (2005)TR No.: 2005012 | Download PDF | Download PS
Abstract:
XCSF is an extension of XCS in which the classifier prediction is computed as a linear combination of classifier inputs and a weight vector associated with each classifier. Recent results show that XCSF exploits the computed prediction and typical XCS generalization pressure to evolve accurate piecewise-linear approximations of functions. The evolved approximations consist of accurate […]
Posted: March 4th, 2005 under Genetic algorithms. Comments: none
Automated Global Structure Extraction For Effective Local Building Block Processing in XCS
Butz, M.V., Pelikan, M., Llorà, X., Goldberg, D.E. (2005)TR No.: 2005011 | Download PDF | Download PS
Abstract:
Learning Classifier Systems (LCSs), such as XCS and other accuracy-based
classifier systems, evolve distributed problem solutions represented by a
population of rules. During evolution, features are specialized, propagated, and recombined to provide increasingly accurate subsolutions. Recently, it was shown that, like in conventional genetic algorithms (GAs), some problems require the processing of subsets of features as
opposed to […]
Posted: February 24th, 2005 under Genetic algorithms. Comments: none
Extracted Global Structure Makes Local Building Block Processing Effective in XCS
Butz, M.V., Pelikan, M., Llorà, X., Goldberg, D.E. (2005)TR No.: 2005010 | Download PDF | Download PS
Abstract:
Learning Classifier Systems (LCSs), such as the accuracy-based XCS system, evolve distributed problem solutions represented by a population of rules.
Recently, it was shown that decomposable problems may require effective processing of feature subsets as opposed to individual features, which cannot be generally assured with standard crossover operators. Although a number of competent crossover operators capable […]
Posted: February 20th, 2005 under Genetic algorithms. Comments: none
Combating User Fatigue in iGAs: Partial Ordering, Support Vector Machines, and Synthetic Fitness
Llorà, X., Sastry, K., Goldberg, D.E., Gupta, A., Lakshmi, L. (2005)TR No.: 2005009 | Download PDF | Download PS
Abstract:
One of the daunting challenges of interactive genetic algorithms
(iGAs)—genetic algorithms in which fitness measure of a solution is
provided by a human rather than by a fitness function, model, or
computation—is user fatigue which leads to sub-optimal
solutions. This paper proposes a method to combat user fatigue by
augmenting user evaluations with a synthetic fitness function. The
proposed method combines […]
Posted: February 16th, 2005 under Genetic algorithms. Comments: none
XCS with Computable Prediction in Multistep Environments
Lanzi, P.-L., Loiacono, D., Wilson, S. W., Goldberg, D. E. (2005)TR No.: 2005008 | Download PDF | Download PS
Abstract:
XCSF extends the typical concept of learning classifier systems through the introduction of computable classifier prediction. Initial results show that XCSF’s computable prediction can be used to evolve accurate piecewise linear approximations of simple functions. In this paper, we take XCSF one step further and apply it to typical reinforcement learning problems involving delayed rewards. […]
Posted: February 12th, 2005 under Genetic algorithms. Comments: none
XCS with Computable Prediction for the Learning of Boolean Functions
Lanzi, P.-L., Loiacono, D., Wilson, S. W., Goldberg, D. E. (2005)TR No.: 2005007 | Download PDF | Download PS
Abstract:
Computable prediction represents a major shift in learning classifier system research. XCS with computable prediction, based on linear approximators, has been applied so far to function approximation problems and to single step problems involving continuous payoff functions. In this paper we take this new approach in a different direction and apply it to the learning […]
Posted: February 8th, 2005 under Genetic algorithms. Comments: none