Thanks @hosford42 for reminding me of this half-day tutorial on Vector Symbolic Architectures / Hyperdimensional Computing. The authors have been applying HDC/VSA to place recognition in robotics, but the tutorial coverage is much wider.

https://www.tu-chemnitz.de/etit/proaut/workshops_tutorials/hdc_ki19/index.html

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CogRob #CognitiveRobotics #CompCogSci #ComputationalCognitiveScience #CogSci #CognitiveScience #MathPsych #MathematicalPsychology

Help from older folk please: In the earlier days of artificial intelligence (GOFAI) - say, the 1980s - there was an aphorism to the effect that once you had found the right data representation for your problem you had pretty much solved your problem (i.e. choice of representation dominates choice of algorithm).

I would greatly appreciate (some approximation to) the actual text of the aphorism and, if possible, some citation to its origin.

Thanks!

#AI #ArtificialIntelligence #GOFAI #GoodOldFashionedAI #aphorisms #sayings #CogSci #CognitiveScience #CompCogSci #ComputationalCognitiveScience

Here are two high level articles that mention Vector Symbolic Architecure / HyperDimensional Computing in the more "popular" end of the technical press:

https://www.quantamagazine.org/a-new-approach-to-computation-reimagines-artificial-intelligence-20230413/

https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10098176

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CompCogSci #ComputationalCognitiveScience #CogSci #CognitiveScience #MathPsych #MathematicalPsychology

High level piece on hyperdimensional computing / Vector Symbolic Architecture in Quanta Magazine:
https://www.quantamagazine.org/a-new-approach-to-computation-reimagines-artificial-intelligence-20230413/

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CompCogSci #CogSci #CognitiveScience

@NicoleCRust field-specific hashtags for paper announcements and threads might not work so well for those of us with poor memories and interests across multiple fields, because we would have to remember the specific hashtags for each field.

The Mastodon advanced web interface allows you to follow combinations of hashtags (instructions here: https://blog.djnavarro.net/posts/2022-11-03_what-i-know-about-mastodon/#tracking-hashtags) but it doesn't appear to allow for (#neuroscience AND (#NewPaper OR #PaperThread)), plus I think I found a bug.

For now, I think I will follow (#PaperThread OR #NewPaper OR #NeuroPaperThread OR #NeuroNewPaper OR ...).

Plus, I'm copying in @cogsci #CogSci and #CompCogSci because this is an issue that needs to be discussed in all research communities.

@dae

Readers of "How is perception tractable?" (https://philpapers.org/archive/BROHIP-2.pdf) might also be interested in "High-level perception, representation, and analogy: A critique of artificial intelligence methodology" (https://www.tandfonline.com/doi/abs/10.1080/09528139208953747), which doesn't touch on computational tractability but does argue that perception is necessarily *not* encapsulated from cognition.

#CogSci #CompCogSci #CognitiveScience #ComputationalCognitiveScience #cognition #analogy @cogsci

@melaniemitchell @cogsci

Boosting with hashtags for my followers. See the original post in the thread above.

International SFI summer school on Intelligence and Representation

For PhD students, in Cambridge, UK, August 13-25, 2023. Tuition is free! Apply by March 1, 2023.

https://santafe.edu/engage/learn/programs/complexity-gains-international-summer-school

#CogSci #CognitiveScience #cognition #CompCogSci #ComputationalCognitiveScience

@DrYohanJohn
@cogsci

Boosting for my followers - see original post in the thread above.

The BBS target article on the Language of Thought Hypothesis states:

"We outline six core properties of
LoTs: (i) discrete constituents; (ii) role-filler independence; (iii) predicate-argument
structure; (iv) logical operators; (v) inferential promiscuity; and (vi) abstract content."

It's interesting to think about the extent to which those properties are directly enabled by neural representations using Vector Symbolic Architectures / Hyperdimensional Computing. It hadn't occurred to me to draw a line between LoT and VSA/HDC.

#CogSci #CognitiveScience #CompCogSci #ComputationalCognitiveScience #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing

Lulea Technical University (Sweden) announces two open positions ultimately focusing on research on hyperdimensional computing and vector-symbolic architectures. The positions are connected to the recently approved grant by Swedish Research Council "Vector-symbolic architectures as an algebraic programming language for neuromorphic computers”.

The application deadline is January 31st, 2023

Position 1. Senior lecturer: https://lnkd.in/gu5zf69T

Position 2. Researcher: https://lnkd.in/giSuqkFi

Should you have any questions please write to Evgeny Osipov (Evgeny.Osipov@ltu.se).

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CogSci #CognitiveScience #CogRob #CognitiveRobotics #MathPsych #CompCogSci #CompSci #ComputerScience #neuromorphic

Lulea Technical University (Sweden) announces two open positions ultimately focusing on research on hyperdimensional computing and vector-symbolic architectures. The positions are connected to the recently approved grant by Swedish Research Council "Vector-symbolic architectures as an algebraic programming language for neuromorphic computers”.

The application deadline is January 31st, 2023

Position 1. Senior lecturer: https://lnkd.in/gu5zf69T

Position 2. Researcher: https://lnkd.in/giSuqkFi

Should you have any questions please write to Evgeny Osipov (Evgeny.Osipov@ltu.se).

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CogSci #CognitiveScience #CogRob #CognitiveRobotics #MathPsych #CompCogSci #CompSci #ComputerScience #neuromorphic
#job

#introduction
I am an independent researcher (i.e. unpaid & unaffiliated) in computational cognitive science (#CompCogSci). This research revolves around Vector Symbolic Architectures (#VSA aka #HDC) - computational systems based on very high dimensional vector spaces, which can be implemented as neural networks and can be thought of as analog computers for manipulating discrete data structures such as trees and graphs. VSAs have interesting and useful algebraic properties by virtue of how they are defined. That is they have these exploitable algebraic properties out of the box, rather than having to be learned.

My research is aimed at developing a practical, implementable, connectionist architecture for compositional memory. Such a memory system would have the ability to recognise novel situations and objects in terms of the novel pattern of structural relationships between their familiar component parts.

This work effectively treats analogy as a primitive capability of memory. Current standard machine-learning techniques have limited capacity to deal with patterns of relationships and consequently have difficulty recognising novel configurations of familiar components or recognising familiar patterns of relationship when the components have been changed.

I am based in Melbourne, Australia.