Dynamic search trajectory methods for neural network training

DOI10.1007/978-3-540-24844-6_32MaRDI QIDQ4666366zbMATH OpenOpenAlexFDO

Authors Y. G. Petalas, Dimitris K. Tasoulis, Michael N. Vrahatis

Publication date 12 April 2005

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/b98109

zbMATH Keywords

Neural Networks TrainingOrdinary Differential EquationsTrajectory Methods

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Dynamical multilayer neural networks that learn continuous trajectories
• A new approach to real‐time training of dynamic neural networks
• Training feedforward networks using simultaneous perturbation with dynamic tunneling

Cited in

(13)

• A homotopy method for training neural networks
• Backpropagation versus dynamic programming approach
• Training feedforward networks using simultaneous perturbation with dynamic tunneling
• Convergence analysis of sliding mode trajectories in multi-objective neural networks learning
• On the overfly algorithm in deep learning of neural networks
• Dynamic search trajectory methods for global optimization
• Memetic particle swarm optimization
• Bounding the search space for global optimization of neural networks learning error: an interval analysis approach
• Gravity training method
• scientific article; zbMATH DE number 2034467 (Why is no real title available?)
• scientific article; zbMATH DE number 2079506 (Why is no real title available?)
• Performance of a coordinate search ANN training algorithm
• Dynamics of temporary minima in a feed-forward neural network

This page was built for publication: Dynamic search trajectory methods for neural network training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4666366)