Thinking about Vector Symbolic Architectures
Slides for the keynote presentation "Thinking about Vector Symbolic Architectures" given on 2023-06-15 at the Midnight Sun Workshop on Vector Symbolic Architectures in Luleå, Sweden. Abstract Vector Symbolic Architectures are defined in terms of a very small set of operators acting on a ve...
Main Author: | |
---|---|
Format: | Conference Object |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://zenodo.org/record/8076707 https://doi.org/10.5281/zenodo.8076707 |
id |
ftzenodo:oai:zenodo.org:8076707 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:8076707 2023-07-16T03:59:28+02:00 Thinking about Vector Symbolic Architectures Gayler, Ross W. 2023-06-15 https://zenodo.org/record/8076707 https://doi.org/10.5281/zenodo.8076707 eng eng doi:10.5281/zenodo.8076736 doi:10.5281/zenodo.8076677 doi:10.5281/zenodo.8076706 https://zenodo.org/record/8076707 https://doi.org/10.5281/zenodo.8076707 oai:zenodo.org:8076707 info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode vsa vector symbolic architecture hdc hyperdimensional computing info:eu-repo/semantics/lecture presentation 2023 ftzenodo https://doi.org/10.5281/zenodo.807670710.5281/zenodo.807673610.5281/zenodo.807667710.5281/zenodo.8076706 2023-06-27T22:59:01Z Slides for the keynote presentation "Thinking about Vector Symbolic Architectures" given on 2023-06-15 at the Midnight Sun Workshop on Vector Symbolic Architectures in Luleå, Sweden. Abstract Vector Symbolic Architectures are defined in terms of a very small set of operators acting on a vector space. The task of the VSA researcher is to discover the implications that follow from the definition in terms of the systems that can be implemented with VSAs. The VSA definitions are the researcher’s raw materials, but they also need tools to transform those raw materials into useful hypotheses and system designs. One important tool for a researcher is a conceptual framework, which specifies how the researcher thinks about VSAs and relates them to the other things they know. It is the researcher’s mental model of how VSAs work. The primary requirement for a conceptual framework is that it is productive; it should make it easy for the researcher to generate interesting hypotheses and designs. These hypotheses and designs don’t have to be correct, just plausible. Beating them into shape is a different part of the research process. Most VSA research papers contain a statement of the VSA definition. Very few mention the researcher’s conceptual framework. In this talk I will sketch out my conceptual framework - how I think about Vector Symbolic Architectures - in the hope that it might be interesting and useful to other researchers. As presented and live-streamed 2023-06-15 (except for addition of final slide with DOIs) Conference Object Luleå Luleå Luleå midnight sun Zenodo |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
English |
topic |
vsa vector symbolic architecture hdc hyperdimensional computing |
spellingShingle |
vsa vector symbolic architecture hdc hyperdimensional computing Gayler, Ross W. Thinking about Vector Symbolic Architectures |
topic_facet |
vsa vector symbolic architecture hdc hyperdimensional computing |
description |
Slides for the keynote presentation "Thinking about Vector Symbolic Architectures" given on 2023-06-15 at the Midnight Sun Workshop on Vector Symbolic Architectures in Luleå, Sweden. Abstract Vector Symbolic Architectures are defined in terms of a very small set of operators acting on a vector space. The task of the VSA researcher is to discover the implications that follow from the definition in terms of the systems that can be implemented with VSAs. The VSA definitions are the researcher’s raw materials, but they also need tools to transform those raw materials into useful hypotheses and system designs. One important tool for a researcher is a conceptual framework, which specifies how the researcher thinks about VSAs and relates them to the other things they know. It is the researcher’s mental model of how VSAs work. The primary requirement for a conceptual framework is that it is productive; it should make it easy for the researcher to generate interesting hypotheses and designs. These hypotheses and designs don’t have to be correct, just plausible. Beating them into shape is a different part of the research process. Most VSA research papers contain a statement of the VSA definition. Very few mention the researcher’s conceptual framework. In this talk I will sketch out my conceptual framework - how I think about Vector Symbolic Architectures - in the hope that it might be interesting and useful to other researchers. As presented and live-streamed 2023-06-15 (except for addition of final slide with DOIs) |
format |
Conference Object |
author |
Gayler, Ross W. |
author_facet |
Gayler, Ross W. |
author_sort |
Gayler, Ross W. |
title |
Thinking about Vector Symbolic Architectures |
title_short |
Thinking about Vector Symbolic Architectures |
title_full |
Thinking about Vector Symbolic Architectures |
title_fullStr |
Thinking about Vector Symbolic Architectures |
title_full_unstemmed |
Thinking about Vector Symbolic Architectures |
title_sort |
thinking about vector symbolic architectures |
publishDate |
2023 |
url |
https://zenodo.org/record/8076707 https://doi.org/10.5281/zenodo.8076707 |
genre |
Luleå Luleå Luleå midnight sun |
genre_facet |
Luleå Luleå Luleå midnight sun |
op_relation |
doi:10.5281/zenodo.8076736 doi:10.5281/zenodo.8076677 doi:10.5281/zenodo.8076706 https://zenodo.org/record/8076707 https://doi.org/10.5281/zenodo.8076707 oai:zenodo.org:8076707 |
op_rights |
info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.5281/zenodo.807670710.5281/zenodo.807673610.5281/zenodo.807667710.5281/zenodo.8076706 |
_version_ |
1771547232516964352 |