Probabilistic Symbol Encoding for Convolutional Associative Memories

Igor Peric, Alexandru Lesi, Daniel Spies, Stefan Ulbrich, Arne Roennau, Marius Zoellner, Ruediger Dillman

2017

Abstract

Vector Symbolic Architectures (VSAs) define a set of operations for association, storage, manipulation and retrieval of symbolic concepts, represented as fixed-length vectors in IRn. A specific instance of VSAs, Holo- graphic Reduced Representations (HRRs), have proven to exhibit properties similar to human short-term mem- ory and as such are interesting for computational modelling. In this paper we extend the HRR approach by introducing implicit, topology-preserving encoding and decoding procedures. We propose to replace unique symbolic representations with symbols based on probability density functions. These symbols must be ran- domly permuted to ensure the uniform distribution of signals across Fourier space where embedding takes place. These novel encoding schemes eliminate the need for so-called clean-up modules after memory re- trieval (e.g., self-organizing maps). Effectively each encoding implicitly represents its scalar symbol, so no further lookup is needed. We further show that our encoding scheme has a positive impact on memory capacity in comparison to the original capacity benchmark for HRRs (Plate, 1995). We also evaluate our memories in two different robotics tasks: visual scene memory and state machine scripting (holographic controllers).

Download


Paper Citation


in Harvard Style

Peric I., Lesi A., Spies D., Ulbrich S., Roennau A., Zoellner M. and Dillman R. (2017). Probabilistic Symbol Encoding for Convolutional Associative Memories.In Proceedings of the 5th International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX, ISBN 978-989-758-270-7, pages 22-29. DOI: 10.5220/0006503000220029


in Bibtex Style

@conference{neurotechnix17,
author={Igor Peric and Alexandru Lesi and Daniel Spies and Stefan Ulbrich and Arne Roennau and Marius Zoellner and Ruediger Dillman},
title={Probabilistic Symbol Encoding for Convolutional Associative Memories},
booktitle={Proceedings of the 5th International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX,},
year={2017},
pages={22-29},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006503000220029},
isbn={978-989-758-270-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX,
TI - Probabilistic Symbol Encoding for Convolutional Associative Memories
SN - 978-989-758-270-7
AU - Peric I.
AU - Lesi A.
AU - Spies D.
AU - Ulbrich S.
AU - Roennau A.
AU - Zoellner M.
AU - Dillman R.
PY - 2017
SP - 22
EP - 29
DO - 10.5220/0006503000220029