Showing papers on "Evolvability published in 1994"

The evolution of evolvability in genetic programming

Abstract: The notion of ``evolvability''---the ability of a population to produce variants fitter than any yet existing---is developed as it applies to genetic algortithms. A theoretical analysis of the dynamics of genetic programming predicts the existence of a novel, emergent selection phenomenon: the evolution of evolvability. This is produced by the proliferation, within programs, of blocks of code that have a higher chance of increasing fitness when added to programs. Selection can then come to mold the variational aspects of the way evolved programs are represented. A model of code proliferation within programs is analyzed to illustrate this effect. The mathematical and conceptual framework includes: the definition of evolvability as a measure of performance for genetic algorithms; application of Price's Covariance and Selection Theorem to show how the fitness function, representation, and genetic operators must interact to produce evolvability---namely, that genetic operators produce offspring with fitnesses specifically correlated with their parent's fitnesses; how blocks of code emerge as a new level of replicator, proliferating as a function of their ``constructional fitness,'' which is distinct from their schema fitness; and how programs may change from innovative code to conservative code as the populations mature. Several new selection techniques and genetic operators are proposed in order to give better control over the evolution of evolvability and improved evolutionary performance.

Emergent phenomena in genetic programming

Abstract: Evolutionary computation systems exhibit various emergent phenomena, primary of which is adaptation. In genetic programming, because of the indeterminate nature of the representation, the evolution of both recombination distributions and representations can emerge from the population dynamics. A review of ideas on these phenomena is presented, including theory on the evolution of evolvability through differential proliferation of subexpressions within programs. An analysis is given of a model of genetic programming dynamics that is supportive of the “Soft Brood Selection” conjecture, which was proposed as a means to counteract the emergence of highly conservative code, and instead favor highly evolvable code.

The unique implications of brood selection for genetic programming

Abstract: In nature it is common for organisms, as quoted from (Kozlowski and Steams, 1989), to "produce many offspring and then neglect, abort, resorb, or eat some of them, or allow them to eat each other." This phenomenon is known variously as soft selection, brood selection, spontaneous abortion, and a host of other terms depending upon both semantics and the stage of ontogeny and/or development at which the culling of offspring takes place. The bottom line of this behavior in nature is the reduction of parental resource investment in offspring who are potentially less fit than others. The use of brood selection in genetic programming was first suggested in (Altenberg, 1993, 1994) as a method to select for representations of CTP with greater evolvability under recombination. We show that brood selection has benefits to artificial genetic systems analogous to those it confers upon biological genetic systems, specifically in terms of conservation of CPU investment and memory investment. >

The Role of Architecture and Evolutionary Development in Accommodating Change

Abstract: Traditional systems engineering processes emphasize controlling changes, and are effective at ensuring the transformation of system requirements into a system implementation that successfully fulfills those requirements. For large information systems, however, the rate of change in missions and technology is now such that a system that successfully meets the original written requirements may be obsolete on delivery. The days of static turnkey systems are gone: systems must continually evolve to adapt to changes in their environment. To support evolutionary systems, certain changes are required in the systems engineering process. Specifically, a shift in emphasis from limiting change to accommodating change is called for. Accordingly, a shift in emphasis from system requirements to the system architecture is needed. This paper discusses the need for evolvability, the role of architecture in enhancing evolvability, and the changes to the systems engineering process needed to support evolutionary systems.

Bionic emergent system based on the complex system included nonlinear factor

Abstract: This paper discusses the requirements for evolvability in complex systems as the natural life systems, using the nonlinear system factors as a cannonical example. Adaptive evolution or learning in such bionic emergent system via near mutant variants depends upon the structure of the corresponding "fitness landscape". In coevolving systems, fitness landscapes themselves deform due to coupling between coevolving partners. Conditions for optimal coevolution may include tuning of landscape structure for the emergence of nonlinear components among the coadapting entities in the systems. These systems are necessary of the generation of emergent properties based on nonlinear behaviors. And so, this behaviors are consisted with nonlinear factors as limit-cycle or chaotic physical process. >