Parallel evolutionary training algorithms for ``hardware-friendly`` neural networks

DOI10.1023/A:1016545907026zbMATH Open1018.68064MaRDI QIDQ698155FDOQ698155

Michael N. Vrahatis, V. P. Plagianakos

Publication date: 18 September 2002

Published in: Natural Computing (Search for Journal in Brave)

Recommendations

• scientific article
• Parallelizing design of application tailored neural networks
• An evolutionary algorithm for parallel mapping of backpropagation learning on heterogeneous processor networks
• Publication:4945605
• A robust evolutionary algorithm for training neural networks

zbMATH Keywords

``hardware-friendly implementations``on-chip traininginteger weight neural networksparallel differential evolution algorithmsthreshold activation functions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonnumerical algorithms (68W05)

Cited In (9)

• Design and resonant frequency calculation of rectangular microstrip antennas
• ADAPTIVE ALGORITHMS FOR NEURAL NETWORK SUPERVISED LEARNING: A DETERMINISTIC OPTIMIZATION APPROACH
• EVOLUTIONARY METHODS FOR THE APPROXIMATION OF THE STABILITY DOMAIN AND FREQUENCY OPTIMIZATION OF CONSERVATIVE MAPS
• Optimizing digital hardware perceptrons for multi-spectral image classification
• Computing Nash equilibria through computational intelligence methods
• Some improvement to the mutation donor of differential evolution
• Hybrid differential evolution and particle swarm optimization for optimal well placement
• An evolutionary algorithm for parallel mapping of backpropagation learning on heterogeneous processor networks
• COMPUTATIONAL INTELLIGENCE METHODS FOR FINANCIAL TIME SERIES MODELING

This page was built for publication: Parallel evolutionary training algorithms for ``hardware-friendly`` neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q698155)