Simulated Evolution and Learning: 7th International Conference, SEAL 2008, Melbourne, Australia, December 7-10, 2008, Proceedings [Paperback]

This LNCS volume contains the papers presented at SEAL 2008, the 7th Int- nationalConference on Simulated Evolutionand Learning,held December 710, 2008, in Melbourne, Australia. SEAL is a prestigious international conference series in evolutionary computation and learning. This biennial event was ?rst held in Seoul, Korea, in 1996, and then in Canberra, Australia (1998), Nagoya, Japan (2000), Singapore (2002), Busan, Korea (2004), and Hefei, China (2006). SEAL 2008 received 140 paper submissions from more than 30 countries. After a rigorous peer-review process involving at least 3 reviews for each paper (i.e., over 420 reviews in total), the best 65 papers were selected to be presented at the conference and included in this volume, resulting in an acceptance rate of about 46%. The papers included in this volume cover a wide range of topics in simulated evolution and learning: from evolutionarylearning to evolutionary optimization, from hybrid systems to adaptive systems, from theoretical issues to real-world applications. They represent some of the latest and best research in simulated evolution and learning in the world.Evolutionary Learning.- Modelling Behaviour Cycles for Life-Long Learning in Motivated Agents.- Breaking the Synaptic Dogma: Evolving a Neuro-inspired Developmental Network.- A New Approach to Adapting Control Parameters in Differential Evolution Algorithm.- A Novel Genetic Algorithm with Orthogonal Prediction for Global Numerical Optimization.- Phylogeny Inference Using a Multi-objective Evolutionary Algorithm with Indirect Representation.- Evolved Look-Up Tables for Simulated DNA Controlled Robots.- Multi-objective Improvement of Software Using Co-evolution and Smart Seeding.- Policy Evolution with Grammatical Evolution.- A PSO Based Adaboost Approach to Object Detection.- Adaptive Non-uniform Distribution of Quantum Particles in mQSO.- Genetically Evolved Fuzzy Rule-Based Classifiers and Application to Automotive Classification.- Improving XCS PlãB