A self-scaling instruction generator using cartesian genetic programming

Authors:
Yang Liu;Gianluca Tempesti;James A. Walker;Jon Timmis;Andrew M. Tyrrell;Paul Bremner
Affiliations:
Department of Electronics, University of York, UK;Department of Electronics, University of York, UK;Department of Electronics, University of York, UK;Department of Electronics, University of York, UK and Department of Computer Science;Department of Electronics, University of York, UK;Bristol Robotics Laboratory, University of the West of England, UK
Venue:
EuroGP'11 Proceedings of the 14th European conference on Genetic programming
Year:
2011

Citing 11
Cited 0

Genetic programming II: automatic discovery of reusable programs

Genetic programming II: automatic discovery of reusable programs
Hierarchical Processing for Evolving Recursive and Modular Programs Using Higher-Order Functions and Lambda Abstraction

Genetic Programming and Evolvable Machines
Genetic Programming and Autoconstructive Evolution with the Push Programming Language

Genetic Programming and Evolvable Machines
Cartesian Genetic Programming

Proceedings of the European Conference on Genetic Programming
Neutrality and the Evolvability of Boolean Function Landscape

EuroGP '01 Proceedings of the 4th European Conference on Genetic Programming
Evolving Recursive Programs by Using Adaptive Grammar Based Genetic Programming

Genetic Programming and Evolvable Machines
Towards evolving industry-feasible intrinsic variability tolerant CMOS designs

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Developments in Cartesian Genetic Programming: self-modifying CGP

Genetic Programming and Evolvable Machines
Automatic code generation on a MOVE processor using Cartesian genetic programming

ICES'10 Proceedings of the 9th international conference on Evolvable systems: from biology to hardware
A fast and elitist multiobjective genetic algorithm: NSGA-II

IEEE Transactions on Evolutionary Computation
Genetic programming and evolutionary generalization

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the past decades, a number of genetic programming techniques have been developed to evolve machine instructions. However, these approaches typically suffer from a lack of scalability that seriously impairs their applicability to real-world scenarios. In this paper, a novel self-scaling instruction generation method is introduced, which tries to overcome the scalability issue by using Cartesian Genetic Programming. In the proposed method, a dual-layer network architecture is created: one layer is used to evolve a series of instructions while the other is dedicated to the generation of loop control parameters.