Elements for a general memory structure: properties of recurrent neural networks used to form situation models

DOI10.1007/s00422-008-0221-5zbMath1145.92305DBLPjournals/bc/MakarovSVHC08OpenAlexW2130012086WikidataQ51890658 ScholiaQ51890658MaRDI QIDQ937740

Manuel G. Velarde, Holk Cruse, Yongli Song, David Hübner, Valeri A. Makarov

Publication date: 15 August 2008

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

Full work available at URL: https://doi.org/10.1007/s00422-008-0221-5

Mathematics Subject Classification ID

Neural biology (92C20) Memory and learning in psychology (91E40)

Related Items (4)

Synchronization of heteroclinic circuits through learning in coupled neural networks ⋮ Compact internal representation of dynamic situations: neural network implementing the causality principle ⋮ Prediction-for-CompAction: navigation in social environments using generalized cognitive maps ⋮ Selforganizing memory: Active learning of landmarks used for navigation

Cites Work

• Selforganizing memory: Active learning of landmarks used for navigation
• MMC -- a new numerical approach to the kinematics of complex manipulators
• Introduction to linear algebra
• Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations
• Modelling memory functions with recurrent neural networks consisting of input compensation units: II. Dynamic situations
• Parameter Space Structure of Continuous-Time Recurrent Neural Networks
• Complex dynamics and the structure of small neural networks
• 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: Elements for a general memory structure: properties of recurrent neural networks used to form situation models