Evolving Beyond Perfection An Investigation of the Effects of LongTerm Evolution on Fractal.pdfVIP

BioSystems 76 (2004) 291–301 Evolving beyond perfection: an investigation of the effects of long-term evolution on fractal gene regulatory networks Peter J. Bentley Department of Computer Science, University College London, Gower Street, London WC1E 6BT, UK Received 28 February 2003; received in revised form 11 July 2003; accepted 1 August 2003 Abstract This paper continues a theme of exploring algorithms based on principles of biological development for tasks such as pattern generation, machine learning and robot control. Previous work has investigated the use of genes expressed as fractal proteins to enable greater evolvability of gene regulatory networks (GRNs). Here, the evolution of such GRNs is investigated further to determine whether evolution exhibits natural tendencies towards efficiency and graceful degradation of developmental programs. Experiments where “perfect” GRNs are evolved for a further thousand generations without the addition of any further selection pressure, confirm this hypothesis. After further evolution, the perfect GRNs operate in a more efficient manner (using fewer proteins) and show an improved ability to function correctly with missing genes. When the algorithm is applied to applications (e.g. robot control) this equates to efficient and fault-tolerant controllers. © 2004 Elsevier Ireland Ltd. All rights reserved. Keywords: Fractal proteins; Self-organizing and self-repairing systems; Evolutionary algorithms; Bio-developmental systems; Gene networks 1. Introduction air and insulating against cold—nature also uses for di- verse purposes such as powerful horns or poison-filled It is a common misconception held by many tha