|InterJournal Complex Systems, 247
|Manuscript Number: |
Submission Date: 981216
|Unicellular Core-Memory Creatures Evolved Using Genetic Algorithms|
Subject(s): CX.13, CX.30, CX.31, CX.35, CX.62, CX.67
Category: Brief Article
A novel machine language genetic programming system which uses one-dimensional core memories is proposed and simulated. The core is compared to a biochemical reaction space, and in imitation of biological molecules, four types of data words (Membrane, Pure data, Operator, and Instruction) are prepared in the core. A program is represented by a sequence of Instructions. During execution of the core, Instructions are transcribed into corresponding Operators, and Operators modify Pure data. The core is hierarchically partitioned into sections by the Membrane data. In the experiment, a simple machine learning problem is prepared for the environment dataset of the creatures (programs), and genetic algorithms are used to modify program information. Breeding of programs which can output the predefined answer is successfully carried out.
|Submit referee report/comment|