Geometric analogue of holographic reduced representation

DOI10.1016/J.JMP.2009.02.005MaRDI QIDQ1044196zbMATH OpenOpenAlexWikidataFDO

Authors Diederik Aerts, Marek Czachor, B. De Moor

Publication date 11 December 2009

Published in Journal of Mathematical Psychology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0710.2611

quantum algorithms Clifford algebras distributed representations binding problem holographic models matrix memories

Psychophysics and psychophysiology; perception (91E30) Quantum algorithms and complexity in the theory of computing (68Q12) Quantum computation (81P68) General and philosophical questions in quantum theory (81P05) Clifford algebras, spinors (15A66)

Abstract: Holographic reduced representations (HRR) are based on superpositions of convolution-bound

n

-tuples, but the

n

-tuples cannot be regarded as vectors since the formalism is basis dependent. This is why HRR cannot be associated with geometric structures. Replacing convolutions by geometric products one arrives at reduced representations analogous to HRR but interpretable in terms of geometry. Variable bindings occurring in both HRR and its geometric analogue mathematically correspond to two different representations of

Z_{2} i m e s ... i m e s Z_{2}

(the additive group of binary

n

-tuples with addition modulo 2). As opposed to standard HRR, variable binding performed by means of geometric product allows for computing exact inverses of all nonzero vectors, a procedure even simpler than approximate inverses employed in HRR. The formal structure of the new reduced representation is analogous to cartoon computation, a geometric analogue of quantum computation.

Recommendations

Cites work

Cited in

(6)

This page was built for publication: Geometric analogue of holographic reduced representation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1044196)