By Topic

# Proceedings of 1995 IEEE International Conference on Evolutionary Computation

## Filter Results

Displaying Results 1 - 25 of 63
• ### Index [of authors]

Publication Year: 1995
| PDF (179 KB)
• ### Genetic operators using viral models

Publication Year: 1995, Page(s):652 - 656 vol.2
Cited by:  Papers (1)
| | PDF (464 KB)

The use of inversion operators based loosely on viral models are compared using the travelling salesman problem. Using statistical methodologies, some of the operators are found to be preferable in that they offered, on average, significantly faster convergence combined with less likelihood to “plateau” early View full abstract»

• ### Evolving neural network controllers

Publication Year: 1995, Page(s):579 - 583 vol.2
| | PDF (476 KB)

An emerging design paradigm uses evolutionary processes to search for optima in design space. The evolutionary technique has the advantage of being a declarative paradigm; the user specifies the task, and a genetic algorithm searches for an optimum solution. Normal techniques require the definition of the controller, and this is computationally expensive. We use a genetic algorithm to design a neu... View full abstract»

• ### Parameterization of a metapopulation model: an empirical comparison of several different genetic algorithms, simulated annealing and tabu search

Publication Year: 1995, Page(s):551 - 556 vol.2
Cited by:  Papers (2)  |  Patents (1)
| | PDF (508 KB)

Analysis of metapopulation dynamics is currently of great interest in population biology and in conservation biology. In this study a metapopulation model is augmented with external environmental factors, which are modelled by a group of polynomials. The parameter estimation of the extended model is attempted with three methods of global optimization, simulated annealing (SA), tabu search (TS) and... View full abstract»

• ### Self-adaptive genetic algorithm learning in game playing

Publication Year: 1995, Page(s):814 - 818 vol.2
Cited by:  Papers (4)
| | PDF (484 KB)

Genetic algorithms (GAs) are known to be effective search methods that are also robust and efficient. We introduce a self-adaptive function for conventional GAs. A dynamic fitness technique helpful for continuous evolution and robust solution is also presented. We expect to improve the quality of GA searches in solving direct competitive problems. We tested our idea by using it to play the game Ot... View full abstract»

• ### Hybridized crossover-based search techniques for program discovery

Publication Year: 1995, Page(s):573 - 578 vol.2
Cited by:  Papers (17)  |  Patents (2)
| | PDF (520 KB)

Addresses the problem of program discovery as defined by genetic programming. By combining a hierarchical crossover operator with two traditional single-point search algorithms (simulated annealing and stochastic iterated hill climbing), we have solved some problems by processing fewer candidate solutions and with a greater probability of success than genetic programming. We have also enhanced gen... View full abstract»

• ### A learning machine that evolves

Publication Year: 1995, Page(s):808 - 813 vol.2
Cited by:  Papers (3)
| | PDF (352 KB)

We propose a simple model of a learning machine that evolves. When a classification problem is given, a perceptron like learning machine obtains a proper set of feature detecting cells through mating, mutation, and natural selection. Computer simulation showed the expected results. This is one of our trials to approach the evolutionary system in the real world View full abstract»

• ### Phenotypic forking genetic algorithm (p-fGA)

Publication Year: 1995, Page(s):566 - 572 vol.2
Cited by:  Papers (3)
| | PDF (572 KB)

Proposes a new type of multi-population genetic algorithm, the p-fGA (phenotypic forking GA), an extension of the previously proposed g-fGA (genotype forking GA). Both the g-fGA and the p-fGA are designed to solve multi-modal problems which are difficult to solve by traditional GAs. We use multi-population schemes that include one parent population with a blocking mode and one or more child popula... View full abstract»

• ### Genetic programming of fuzzy logic production rules

Publication Year: 1995, Page(s):765 - 770 vol.2
Cited by:  Papers (1)
| | PDF (340 KB)

John Koza (1992) demonstrated that a form of machine learning could be constructed by using the techniques of evolutionary computation with LISP statements. We describe an extension to this principle using fuzzy logic sets and operations instead of LISP. We show that genetic programming can be used to generate trees of fuzzy logic statements that optimise some external process, that these can be c... View full abstract»

• ### On GA-based optimal fuzzy control

Publication Year: 1995, Page(s):846 - 851 vol.2
| | PDF (352 KB)

Two architectures for designing optimal fuzzy control systems are proposed. In both cases, the membership functions in the fuzzy rule bases are tuned by the genetic algorithms. The objective is to explore a fuzzy controller by minimizing a quadratic cost function. In the first architecture, the employed controller is a conventional fuzzy logic controller which uses the system states as input varia... View full abstract»

• ### Learning to achieve co-operation by temporal-spatial fitness sharing

Publication Year: 1995, Page(s):803 - 807 vol.2
| | PDF (348 KB)

We propose a co-operative GA-based learning system that would make real-world heterogeneous agents feasible with the minimum amount of communication hardware. The problem is identical to a distributed GA implemented on processors connected by local and very slow communication lines. We have developed an extension of the fitness sharing method that incorporates sharing over temporally-spatially dis... View full abstract»

• ### A fitness scaling method based on a span measure

Publication Year: 1995, Page(s):561 - 565 vol.2
Cited by:  Papers (2)
| | PDF (324 KB)

This paper describes a new fitness scaling method based on a characteristic of a population of chromosomes known as the span. This transformation is both scale and translation invariant. Its behavior is illustrated on two complex multimodal functions and a comparison is provided with a power law scaling method View full abstract»

• ### A fuzzy classifier system that generates fuzzy if-then rules for pattern classification problems

Publication Year: 1995, Page(s):759 - 764 vol.2
Cited by:  Papers (29)
| | PDF (508 KB)

We propose a fuzzy classifier system that can automatically generate fuzzy if-then rules from numerical data (i.e., from training patterns) for multi-dimensional pattern classification problems. Classifiers in our approach are fuzzy if-then rules such as “If x p1 is small and xp2 is large then classify xp as Class 2”. The proposed classifier system can... View full abstract»

• ### Evolving facial expressions

Publication Year: 1995, Page(s):515 - 520 vol.2
Cited by:  Papers (1)
| | PDF (916 KB)

The interactive evolution technique, a variation of genetic algorithms, is used in synthesizing various facial expressions from an input 2D image of a face. Smooth 2D transformations were used to compensate for changes in facial expressions. The large space of the transformations or facial expressions is searched through by interactive evolution, without tedious user specifications, design efforts... View full abstract»

• ### Genetic algorithm-based optimization of fuzzy logic controller using characteristic parameters

Publication Year: 1995, Page(s):831 - 836 vol.2
Cited by:  Papers (4)  |  Patents (1)
| | PDF (456 KB)

A novel optimization algorithm of fuzzy logic controller (FLC) using genetic algorithms (GAs) is proposed. To characterize the major design parameters of an FLC, characteristic parameters are defined which can greatly simplify the design procedure of the FLC. The characteristic parameters are encoded into a chromosome presented as an integer string. The chromosomes are then optimized by maximizing... View full abstract»

• ### Designing max-min propagation neural networks by hyperplane switching

Publication Year: 1995, Page(s):596 - 601 vol.2
| | PDF (336 KB)

A method for synthesizing max-min propagation neural networks by using genetic algorithms is proposed. These networks are viewed as switching among hyperplanes and the switching configurations are evolved. A distance measure between n-ary strings of variable length is introduced. This metric is used in a niching algorithm to find multiple optima in the space of architectures. Simulation results on... View full abstract»

• ### Evolving polydistributional mixtures for mammographic feature modeling and analysis

Publication Year: 1995, Page(s):783 - 787 vol.2
| | PDF (436 KB)

This work investigates the application of stochastic optimization in the development of a new paradigm, polydistributional mixtures, for automated data modeling. This new paradigm increases the generality of mixture methods by allowing for the automated simultaneous optimization of the number of components, the distributional form of each component, the proportionality associated with each compone... View full abstract»

• ### Solving randomly generated constraint satisfaction problems using a micro-evolutionary hybrid that evolves a population of hill-climbers

Publication Year: 1995, Page(s):614 - 619 vol.2
Cited by:  Papers (8)
| | PDF (524 KB)

This paper introduces a new micro-evolutionary search technique which combines the concept of evolutionary searching with the systematic search concept of hill climbing to form a hybrid that quickly find solutions to constraint satisfaction problems. This new hybrid outperforms a well-known hill climber, the iterative descent method (IDM), on a test suite of 750 randomly-generated constraint satis... View full abstract»

• ### An expansion operator for interactive evolution

Publication Year: 1995, Page(s):798 - 802 vol.2
Cited by:  Papers (5)
| | PDF (560 KB)

We demonstrate how interactive evolution can be applied to the extrapolation and growth of graphical models. In addition to the mutation and recombination operator for interactive evolution, we introduce a new operator termed expansion and show it to play a significant role in interactive evolution. The expansion operator predicts new future models on the basis of time series analyses of evolution... View full abstract»

• ### Genetic algorithms incorporating a pseudo-subspace method

Publication Year: 1995, Page(s):557 - 560 vol.2
| | PDF (412 KB)

GA performance in high-dimensional optimisation problems can be enhanced by the use of a pseudo subspace' technique. The method works by projecting the parameter space onto a lower dimensional subspace in the first stages of the optimisation process, in order to allow the GA search to discover the most promising area of the solution space. Subsequently, the dimensionality of the model is progress... View full abstract»

• ### Genocop III: a co-evolutionary algorithm for numerical optimization problems with nonlinear constraints

Publication Year: 1995, Page(s):647 - 651 vol.2
Cited by:  Papers (79)  |  Patents (4)
| | PDF (388 KB)

During the last two years several methods have been proposed for handling nonlinear constraints by genetic algorithms for numerical optimization problems; most of them were based on penalty functions. However, the performance of these methods is highly problem-dependent; moreover, many methods require additional tuning of several parameters. We present a new optimization system (Genocop III), whic... View full abstract»

• ### Evolutionary variable step-size algorithm for adaptive filtering

Publication Year: 1995, Page(s):663 - 667 vol.2
Cited by:  Papers (2)
| | PDF (408 KB)

A new variable step size scheme namely evolutionary variable step-size algorithm (EVS) for adaptive filtering is proposed. The algorithm is basically a kind of evolutionary method based on evolving the step size of the least-mean-square (LMS) algorithm. The step size candidates are generated by random or deterministic perturbation and then evaluated by calculating a square error measure based on a... View full abstract»

• ### Performance measures in the genetic design of digital controllers for robotic manipulators

Publication Year: 1995, Page(s):509 - 514 vol.2
| | PDF (336 KB)

Genetic algorithms are used to design digital multivariable PID controllers for robotic manipulators for typical trajectory-tracking tasks when various different performance measures are used. It is thus shown that, by using an appropriate performance measure, the set of controller parameters can be readily found that determines the optimal time-domain trajectory-tracking behaviour for such tasks.... View full abstract»

• ### The application of evolution strategies to the problem of parameter optimization in fuzzy rulebased systems

Publication Year: 1995, Page(s):825 - 830 vol.2
Cited by:  Papers (4)  |  Patents (1)
| | PDF (600 KB)

Fuzzy logic has become widely acknowledged as an important and useful methodology in the design of rule based systems. It allows the representation of imprecise or incomplete knowledge and offers various mechanisms for reasoning with fuzzy data. In comparison to classical' rule based systems, only very few rules are needed to describe difficult problems. Nevertheless, in its current form it has s... View full abstract»

• ### Evolving complex neural networks that age

Publication Year: 1995, Page(s):590 - 595 vol.2
| | PDF (468 KB)

The combination of the broad problem-searching capabilities of a genetic algorithm with the local maxima location capabilities of a hill-climbing algorithm can be a powerful technique for solving classification problems. Producing a number of specialist artificial neural networks, each an expert on one category, can be beneficial when solving problems in which the categories are distinct. This pap... View full abstract»