Adapting Hardware Systems By Means Of Multi Objective Evolution
Download Adapting Hardware Systems By Means Of Multi Objective Evolution PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Adapting Hardware Systems By Means Of Multi Objective Evolution book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Adapting Hardware Systems by Means of Multi-Objective Evolution
Reconfigurable circuit devices have opened up a fundamentally new way of creating adaptable systems. Combined with artificial evolution, reconfigurable circuits allow an elegant adaptation approach to compensating for changes in the distribution of input data, computational resource errors, and variations in resource requirements. Referred to as "Evolvable Hardware" (EHW), this paradigm has yielded astonishing results for traditional engineering challenges and has discovered intriguing design principles, which have not yet been seen in conventional engineering. In this thesis, we present new and fundamental work on Evolvable Hardware motivated by the insight that Evolvable Hardware needs to compensate for events with different change rates. To solve the challenge of different adaptation speeds, we propose a unified adaptation approach based on multi-objective evolution, evolving and propagating candidate solutions that are diverse in objectives that may experience radical changes. Focusing on algorithmic aspects, we enable Cartesian Genetic Programming (CGP) model, which we are using to encode Boolean circuits, for multi-objective optimization by introducing a meaningful recombination operator. We improve the scalability of CGP by objectives scaling, periodization of local- and global-search algorithms, and the automatic acquisition and reuse of subfunctions using age- and cone-based techniques. We validate our methods on the applications of adaptation of hardware classifiers to resource changes, recognition of muscular signals for prosthesis control and optimization of processor caches.
Inspired by Nature
This book is a tribute to Julian Francis Miller’s ideas and achievements in computer science, evolutionary algorithms and genetic programming, electronics, unconventional computing, artificial chemistry and theoretical biology. Leading international experts in computing inspired by nature offer their insights into the principles of information processing and optimisation in simulated and experimental living, physical and chemical substrates. Miller invented Cartesian Genetic Programming (CGP) in 1999, from a representation of electronic circuits he devised with Thomson a few years earlier. The book presents a number of CGP’s wide applications, including multi-step ahead forecasting, solving artificial neural networks dogma, approximate computing, medical informatics, control engineering, evolvable hardware, and multi-objective evolutionary optimisations. The book addresses in depth the technique of ‘Evolution in Materio’, a term coined by Miller and Downing, using a range of examples of experimental prototypes of computing in disordered ensembles of graphene nanotubes, slime mould, plants, and reaction diffusion chemical systems. Advances in sub-symbolic artificial chemistries, artificial bio-inspired development, code evolution with genetic programming, and using Reed-Muller expansions in the synthesis of Boolean quantum circuits add a unique flavour to the content. The book is a pleasure to explore for readers from all walks of life, from undergraduate students to university professors, from mathematicians, computer scientists and engineers to chemists and biologists.
Advances in Computation and Intelligence
Author: Zhihua Cai
language: en
Publisher: Springer Science & Business Media
Release Date: 2010-10-06
Volumes CCIS 107 and LNCS 6382 constitute the proceedings of the 5th International Symposium, ISICA 2010, held in Wuhan, China, in October 2010. ISICA 2010 attracted 267 submissions and through rigorous reviews 53 papers were included in LNCS 6382. The papers are presented in sections on ANT colony and particle swarm optimization, differential evolution, distributed computing, genetic algorithms, multi-agent systems, multi-objective and dynamic optimization, robot intelligence, statistic learning and system design.