FREEMAN'S K MODELS AS RESERVOIR COMPUTING ARCHITECTURES

DOI10.1142/S179300570900126XMaRDI QIDQ3620276zbMATH OpenOpenAlexFDO

Authors Mustafa C. Ozturk, Jose C. Principle

Publication date 14 April 2009

Published in New Mathematics and Natural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/s179300570900126x

zbMATH Keywords

Freeman K setsliquid state mechanicsuniversal computing machines

Mathematics Subject Classification ID

Recommendations

• Reservoir Computing
• A substrate-independent framework to characterize reservoir computers
• Reservoir computing approaches to recurrent neural network training
• An experimental unification of reservoir computing methods
• Reservoir optimization in recurrent neural networks using properties of Kronecker product
• On the characteristics and structures of dynamical systems suitable for reservoir computing
• scientific article; zbMATH DE number 7164779
• The role of structure and complexity on reservoir computing quality

Cites work

• An associative memory readout for ESNs with applications to dynamical pattern recognition
• Analysis and Design of Echo State Networks
• Computation in a reduced KII network based on synchronization
• Neurons with graded response have collective computational properties like those of two-state neurons
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• TUTORIAL ON NEUROBIOLOGY: FROM SINGLE NEURONS TO BRAIN CHAOS

This page was built for publication: FREEMAN'S K MODELS AS RESERVOIR COMPUTING ARCHITECTURES

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3620276)