Vector-derived transformation binding: an improved binding operation for deep symbol-like processing in neural networks

DOI10.1162/NECO_A_01179MaRDI QIDQ5154150zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Jan Gosmann, Chris Eliasmith

Publication date 1 October 2021

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_01179

Mathematics Subject Classification ID

Networks and circuits as models of computation; circuit complexity (68Q06) Biologically inspired models of computation (DNA computing, membrane computing, etc.) (68Q07) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Optimal Quadratic Binding for Relational Reasoning in Vector Symbolic Neural Architectures
• Representing objects, relations, and sequences
• Tensor product variable binding and the representation of symbolic structures in connectionist systems
• Resonator networks. I: An efficient solution for factoring high-dimensional, distributed representations of data structures
• Binding and normalization of binary sparse distributed representations by context-dependent thinning

Cites work

• Tensor product variable binding and the representation of symbolic structures in connectionist systems

Cited in

(4)

• Resonator networks. I: An efficient solution for factoring high-dimensional, distributed representations of data structures
• Simulating and predicting dynamical systems with spatial semantic pointers
• Representing objects, relations, and sequences
• Optimal Quadratic Binding for Relational Reasoning in Vector Symbolic Neural Architectures

This page was built for publication: Vector-derived transformation binding: an improved binding operation for deep symbol-like processing in neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5154150)