Evolving genetic code

Cooperative Co-Evolving Neural Networks for Robosoccer Simulation

Driving change: the evolution of alternative genetic codes.

Pioneering studies in the 1960s that elucidated the genetic code suggested that all extant forms of life use the same genetic code. This early presumption has subsequently been challenged by the discovery of deviations of the universal genetic code in prokaryotes, eukaryotic nuclear genomes and mitochondrial genomes. These studies have revealed that the genetic code is still evolving despite st...

Grammatical Evolution by Grammatical Evolution: The Evolution of Grammar and Genetic Code

This study examines the possibility of evolving the grammar that Grammatical Evolution uses to specify the construction of a syntactically correct solution. As the grammar dictates the space of symbols that can be used in a solution, its evolution represents the evolution of the genetic code itself. Results provide evidence to show that the coevolution of grammar and genetic code with a solutio...

Towards Byte Code Genetic Programming

We investigate using the GP paradigm to evolve linear genotypes (individuals) that consist of Java byte code. Our prototype GP system (bcGP) is implemented in Java. The evolutionary process is done completely in memory and the fitness of individuals is determined by directly executing them in the Java Virtual Machine (JVM). Our scheme is an effective means for evolving native machine code for t...

Optimising Existing Software with Genetic Programming

We show genetic improvement of programs (GIP) can scale by evolving increased performance in a widely-used and highly complex 50 000 line system. GISMOE found code that is 70 times faster (on average) and yet is at least as good functionally. Indeed it even gives a small semantic gain.