Hyperdimensional Representations in Semiotic Approach to AGI
2020 (English)In: Artificial General Intelligence: 13th International Conference, AGI 2020, St. Petersburg, Russia, September 16–19, 2020, Proceedings / [ed] Ben Goertzel, Aleksandr I. Panov, Alexey Potapov, Roman Yampolskiy, Springer, 2020, p. 231-241Conference paper, Published paper (Refereed)
Abstract [en]
The paper is dedicated to the use of distributed hyperdimensional vectors to represent sensory information in the sign-based cognitive architecture, in which the image component of a sign is encoded by a causal matrix. The hyperdimensional representation allows us to update the precedent dimension of the causal matrix and accumulate information in it during the interaction of the system with the environment. Due to the high dimensionality of vectors, it is possible to reduce the representation and reasoning on the entities related to them to simple operations on vectors. In this work we show how hyperdimensional representations are embedded in an existing sign formalism and provide examples of visual scene encoding.
Place, publisher, year, edition, pages
Springer, 2020. p. 231-241
Series
Lecture Notes in Artificial Intelligence, ISSN 0302-9743, E-ISSN 1611-3349 ; 12177
Keywords [en]
Cognitive agent, Sign-based world model, Semiotic network, Causal tensor, Distributed representation, Symbol grounding
National Category
Computer Sciences
Research subject
Dependable Communication and Computation Systems
Identifiers
URN: urn:nbn:se:ltu:diva-80660DOI: 10.1007/978-3-030-52152-3_24Scopus ID: 2-s2.0-85088497423OAI: oai:DiVA.org:ltu-80660DiVA, id: diva2:1463447
Conference
13th Conference on Artificial Intelligence (AGI 2020), 16–19 September, 2020, St. Petersburg, Russia
Note
ISBN för värdpublikation: 978-3-030-52151-6, 978-3-030-52152-3
2020-09-022020-09-022020-09-02Bibliographically approved