A real time learning algorithm for recurrent analog neural networks

DOI10.1007/BF00198098zbMath0686.92010WikidataQ114961206 ScholiaQ114961206MaRDI QIDQ1262830

Masa-aki Sato

Publication date: 1990

Published in: Biological Cybernetics (Search for Journal in Brave)

zbMATH Keywords

learning algorithmsteady stateback propagation methodrecurrent analog neural networkstotal error of neuron outputs

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Other natural sciences (mathematical treatment) (92F05) Physiological, cellular and medical topics (92Cxx)

Related Items (4)

Classification of temporal trajectories by continuous-time recurrent nets ⋮ An adaptive fuzzy system for modeling chaos ⋮ Reinforcement learning for a biped robot based on a CPG-actor-critic method ⋮ Neural networks for control systems - a survey

Cites Work

• Unnamed Item
• A hierarchical neural-network model for control and learning of voluntary movement
• Self-organization and associative memory
• ``Neural computation of decisions in optimization problems
• Function-space quasi-Newton algorithms for optimal control problems with bounded controls and singular arcs
• Neural theory of association and concept-formation
• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• An Adaptive Associative Memory Principle
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.

This page was built for publication: A real time learning algorithm for recurrent analog neural networks