Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning

DOI10.1162/089976601300014592zbMath0973.68204WikidataQ56864429 ScholiaQ56864429MaRDI QIDQ2708447

É. M. Kussul', Dmitri Rachkovskij

Publication date: 17 April 2001

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: http://cogprints.org/1240/1/cdt-1sp.pdf

zbMATH Keywords

distributed representations; neural network implementations; thinning procedures

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Some approaches to analogical mapping with structure-sensitive distributed representations, A Theory of Sequence Indexing and Working Memory in Recurrent Neural Networks, Memory Capacities for Synaptic and Structural Plasticity, Representing Objects, Relations, and Sequences, Randomized projective methods for the construction of binary sparse vector representations, Increasing the semantic storage density of sparse distributed memory, Time of searching for similar binary vectors in associative memory, A binding procedure for distributed binary data representations, Representation and Extrapolation in Multilayer Perceptrons, Resonator Networks, 1: An Efficient Solution for Factoring High-Dimensional, Distributed Representations of Data Structures, Images, Frames, and Connectionist Hierarchies, The Problem of Rapid Variable Creation

Cites Work

• On associative memory
• Tensor product variable binding and the representation of symbolic structures in connectionist systems
• Neural networks and physical systems with emergent collective computational abilities.