#hyperdimensionalcomputing — Public Fediverse posts

@giacomoi @albertcardona @RuthMalan

I am hoping to see lots more practical developments along the lines of: This physical phenomenon does something (by virtue of being itself) that is isomorphic to some computation. How do we couple it to the environment so that the naturally occurring computation corresponds to something we care about?

To be honest, I am a little surprised that there haven't been more attempts at modern analog computers. This paper by Jaeger et al gives some clue as to the potential for extracting computational services from physic: http://arxiv.org/abs/2307.15408

I suspect that one contributor to the lack of progress on modern analog computing is the difficulty of mapping from the user's problem of interest to the computation offered by the physical substrate. In the AOC case you need to map the user's problem to a fix-point problem (because that's all the hardware can solve). This paper by Kleyko et al deals with that issue by proposing that Vector Symbolic Architectures could be used as an intermediate abstraction between the user's problem and a wide range of nonstandard computational hardware: http://arxiv.org/abs/2106.05268

#neuromorphic #AnalogComputing #VectorSymbolicArchitectures #VSA #HyperdimensionalComputing #HDC

@giacomoi @albertcardona @RuthMalan

I am hoping to see lots more practical developments along the lines of: This physical phenomenon does something (by virtue of being itself) that is isomorphic to some computation. How do we couple it to the environment so that the naturally occurring computation corresponds to something we care about?

To be honest, I am a little surprised that there haven't been more attempts at modern analog computers. This paper by Jaeger et al gives some clue as to the potential for extracting computational services from physic: http://arxiv.org/abs/2307.15408

I suspect that one contributor to the lack of progress on modern analog computing is the difficulty of mapping from the user's problem of interest to the computation offered by the physical substrate. In the AOC case you need to map the user's problem to a fix-point problem (because that's all the hardware can solve). This paper by Kleyko et al deals with that issue by proposing that Vector Symbolic Architectures could be used as an intermediate abstraction between the user's problem and a wide range of nonstandard computational hardware: http://arxiv.org/abs/2106.05268

#neuromorphic #AnalogComputing #VectorSymbolicArchitectures #VSA #HyperdimensionalComputing #HDC

⚡ AI running 23,000× more efficiently?
That’s not a typo — it’s the power of HyDra! 🧠

By merging memory and computation, HyDra revolutionizes hyperdimensional computing for real-world edge AI.

Which everyday device would you love to make smarter (without draining the battery)? 🤔

Explore the full innovation here ➡️ https://blueheadline.com/future-tech/hydra-saves-energy-ai-efficiency/

#Technology #Innovation #AI #FutureTech #HyperdimensionalComputing #BlueHeadline #InMemoryComputing #ChipDesign #EnergyEfficiency #EdgeAI

⚡ AI running 23,000× more efficiently?
That’s not a typo — it’s the power of HyDra! 🧠

By merging memory and computation, HyDra revolutionizes hyperdimensional computing for real-world edge AI.

Which everyday device would you love to make smarter (without draining the battery)? 🤔

Explore the full innovation here ➡️ https://blueheadline.com/future-tech/hydra-saves-energy-ai-efficiency/

#Technology #Innovation #AI #FutureTech #HyperdimensionalComputing #BlueHeadline #InMemoryComputing #ChipDesign #EnergyEfficiency #EdgeAI

The next VSAonline webinar is at 17:00 UTC (not the usual time), Monday 27 January.

Zoom: https://ltu-se.zoom.us/j/65564790287

WEB: https://bit.ly/vsaonline

Speaker: Anthony Thomas from UC Davis, USA

Title: ”Sketching a Picture of Vector Symbolic Architectures”

Abstract : Sketching algorithms are a broad area of research in theoretical computer science and numerical analysis that aim to distil data into a simple summary, called a "sketch," that retains some essential notion of structure while being much more efficient to store, query, and transmit.

Vector-symbolic architectures (VSAs) are an approach to computing on data represented using random vectors, and provide an elegant conceptual framework for realizing a wide variety of data structures and algorithms in a way that lends itself to implementation in highly-parallel and energy-efficient computer hardware.

Sketching algorithms and VSA have a substantial degree of consonance in their methods, motivations, and applications. In this tutorial style talk, I will discuss some of the connections between these two fields, focusing, in particular, on the connections between VSA and tensor-sketches, a family of sketching algorithms concerned with the setting in which the data being sketched can be decomposed into Kronecker (tensor) products between more primitive objects. This is exactly the situation of interest in VSA and the two fields have arrived at strikingly similar solutions to this problem.

#VectorSymbolicArchitectures #VSA #HyperdimensionalComputing #HDC #AI #ML #ComputationalCognitiveScience #CompCogSci #MathematicalPsychology #MathPsych #CognitiveScience #CogSci @cogsci

The next VSAonline webinar is at 17:00 UTC (not the usual time), Monday 27 January.

Zoom: https://ltu-se.zoom.us/j/65564790287

WEB: https://bit.ly/vsaonline

Speaker: Anthony Thomas from UC Davis, USA

Title: ”Sketching a Picture of Vector Symbolic Architectures”

Abstract : Sketching algorithms are a broad area of research in theoretical computer science and numerical analysis that aim to distil data into a simple summary, called a "sketch," that retains some essential notion of structure while being much more efficient to store, query, and transmit.

Vector-symbolic architectures (VSAs) are an approach to computing on data represented using random vectors, and provide an elegant conceptual framework for realizing a wide variety of data structures and algorithms in a way that lends itself to implementation in highly-parallel and energy-efficient computer hardware.

Sketching algorithms and VSA have a substantial degree of consonance in their methods, motivations, and applications. In this tutorial style talk, I will discuss some of the connections between these two fields, focusing, in particular, on the connections between VSA and tensor-sketches, a family of sketching algorithms concerned with the setting in which the data being sketched can be decomposed into Kronecker (tensor) products between more primitive objects. This is exactly the situation of interest in VSA and the two fields have arrived at strikingly similar solutions to this problem.

#VectorSymbolicArchitectures #VSA #HyperdimensionalComputing #HDC #AI #ML #ComputationalCognitiveScience #CompCogSci #MathematicalPsychology #MathPsych #CognitiveScience #CogSci @cogsci

The schedule for the next VSAonline webinar series (January to June 2025) is published at:

https://sites.google.com/view/hdvsaonline/spring-2025

There are 11 talks around #VectorSymbolicArchitecture / #HyperdimensionalComputing

The talks are (almost always) recorded and published online, in case you can't participate in the live session.

@cogsci
#VSA #HDC #CompCogScii #MathPsych #AI #neuromorphic #neurosymbolic #ComputationalNeuroscience #ComputationalCognitiveScience #MathematicalPsychology

The schedule for the next VSAonline webinar series (January to June 2025) is published at:

https://sites.google.com/view/hdvsaonline/spring-2025

There are 11 talks around #VectorSymbolicArchitecture / #HyperdimensionalComputing

The talks are (almost always) recorded and published online, in case you can't participate in the live session.

@cogsci
#VSA #HDC #CompCogScii #MathPsych #AI #neuromorphic #neurosymbolic #ComputationalNeuroscience #ComputationalCognitiveScience #MathematicalPsychology

I was looking through the VSAonline website (https://sites.google.com/view/hdvsaonline/home) and saw that by the end of this year there will be 96 recorded webinars plus the recordings from the Midnight Sun 2023 workshop.

So, if you're interested in #VectorSymbolicArchitecture / #HyperdimensionalComputing or just #VSA / #HDC -curious, the VSAonline website is the place to go (or head over to https://www.hd-computing.com/home, where there's a wider range of resources, including publication lists).

#CognitiveScience #CogSci #ComputationalCognitiveScience #CompCogSci #AI #ArtificialIntelligence #ML #MachineLearning #neuromorphic #ComputationalNeuroscience

I was looking through the VSAonline website (https://sites.google.com/view/hdvsaonline/home) and saw that by the end of this year there will be 96 recorded webinars plus the recordings from the Midnight Sun 2023 workshop.

So, if you're interested in #VectorSymbolicArchitecture / #HyperdimensionalComputing or just #VSA / #HDC -curious, the VSAonline website is the place to go (or head over to https://www.hd-computing.com/home, where there's a wider range of resources, including publication lists).

#CognitiveScience #CogSci #ComputationalCognitiveScience #CompCogSci #AI #ArtificialIntelligence #ML #MachineLearning #neuromorphic #ComputationalNeuroscience

If you're (potentially) interested in Vector Symbolic Architectures / Hyperdimensional Computing and Artificial Intelligence and you're within reach of Palo Alto, California on June 12th then you should head along to the event being hosted by Nordic Innovation House. Some of my colleagues from UC Berkeley and Luleå Tekniska Universitet will be there.

https://www.eventbrite.com/e/hypervectors-agi-event-tickets-876530936627

#event #meeting #VectorSymbolicArchitectures #VSA #HyperdimensionalComputing #HDC #ArtificialIntelligence #AI #ArtificialGeneralIntelligence #AGI

If you're (potentially) interested in Vector Symbolic Architectures / Hyperdimensional Computing and Artificial Intelligence and you're within reach of Palo Alto, California on June 12th then you should head along to the event being hosted by Nordic Innovation House. Some of my colleagues from UC Berkeley and Luleå Tekniska Universitet will be there.

https://www.eventbrite.com/e/hypervectors-agi-event-tickets-876530936627

#event #meeting #VectorSymbolicArchitectures #VSA #HyperdimensionalComputing #HDC #ArtificialIntelligence #AI #ArtificialGeneralIntelligence #AGI

**Submission deadline extended to 2024-01-29**

Antonello Rosato (Sapienza University of Rome) has organised a half-day workshop on Vector Symbolic Architectures / Hyperdimensional Computing, to be held in Valencia, Spain, on 27 March 2024 as part of the Design, Automation and Test in Europe Conference (DATE24):
https://www.date-conference.com/workshop/w05
#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing
#CogSci #CognitiveScience #CogRob #CognitiveRobotics #AI #ArtificialIntelligence #neuromorphic

**Submission deadline extended to 2024-01-29**

Antonello Rosato (Sapienza University of Rome) has organised a half-day workshop on Vector Symbolic Architectures / Hyperdimensional Computing, to be held in Valencia, Spain, on 27 March 2024 as part of the Design, Automation and Test in Europe Conference (DATE24):
https://www.date-conference.com/workshop/w05
#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing
#CogSci #CognitiveScience #CogRob #CognitiveRobotics #AI #ArtificialIntelligence #neuromorphic

Here's a really interesting (long) paper on what a theory of computing based on arbitrary physical substrates might look like: http://arxiv.org/abs/2307.15408

"Toward a formal theory for computing machines made out of whatever physics offers: extended version"

Herbert Jaeger, Beatriz Noheda, Wilfred G. van der Wiel (2023)

@bnoheda

#NewPaper #TheoreticalComputerScience #neuromorphic #CogSci #CognitiveScience #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #AnalogComputing

Here's a really interesting (long) paper on what a theory of computing based on arbitrary physical substrates might look like: http://arxiv.org/abs/2307.15408

"Toward a formal theory for computing machines made out of whatever physics offers: extended version"

Herbert Jaeger, Beatriz Noheda, Wilfred G. van der Wiel (2023)

@bnoheda

#NewPaper #TheoreticalComputerScience #neuromorphic #CogSci #CognitiveScience #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #AnalogComputing

@thezerobit for fielded devices I gotta agree. However, for algorithmic explanation of an approach to computing that might *actually* be well suited to memristors (and other proposed noisy hardware technologies) there's a reasonable amount of activity in the Vector Symbolic Architecture / Hyperdimensional Computing space:

https://duckduckgo.com/?t=h_&q=memristor+%22vector+symbolic+architecture%22+&ia=web

https://duckduckgo.com/?t=h_&q=memristor+hyperdimensional+&ia=web

#memristor #neuromorphic #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing

@thezerobit for fielded devices I gotta agree. However, for algorithmic explanation of an approach to computing that might *actually* be well suited to memristors (and other proposed noisy hardware technologies) there's a reasonable amount of activity in the Vector Symbolic Architecture / Hyperdimensional Computing space:

https://duckduckgo.com/?t=h_&q=memristor+%22vector+symbolic+architecture%22+&ia=web

https://duckduckgo.com/?t=h_&q=memristor+hyperdimensional+&ia=web

#memristor #neuromorphic #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing

New paper with the Rosing group at UCSD: we use #HyperdimensionalComputing and GPU Tensor Cores to speed up #OpenModificationSearching by orders of magnitude. Search a raw file in a matter of seconds! 🔥

Out now in #Bioinformatics: https://doi.org/10.1093/bioinformatics/btad404

#proteomics #massspectrometry

New paper with the Rosing group at UCSD: we use #HyperdimensionalComputing and GPU Tensor Cores to speed up #OpenModificationSearching by orders of magnitude. Search a raw file in a matter of seconds! 🔥

Out now in #Bioinformatics: https://doi.org/10.1093/bioinformatics/btad404

#proteomics #massspectrometry

The videos of the talks from the Midnight Sun Workshop on Vector Symbolic Architectures and Hyperdimensional Computing are now online at:

https://sites.google.com/ltu.se/midnightvsa/abstracts?authuser=0

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CogSci #CognitiveScience #neuromorphic #UnconventionalComputing

The videos of the talks from the Midnight Sun Workshop on Vector Symbolic Architectures and Hyperdimensional Computing are now online at:

https://sites.google.com/ltu.se/midnightvsa/abstracts?authuser=0

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CogSci #CognitiveScience #neuromorphic #UnconventionalComputing

Check out HyperSpec, our super-duper-ultrafast spectrum clustering tool based on #HyperdimensionalComputing! ⚡

This was a fun collaboration with the Rosing lab at UC San Diego, who are wizards in using advanced hardware to optimize complex computations.

OA paper: https://pubs.acs.org/doi/10.1021/acs.jproteome.2c00612

Check out HyperSpec, our super-duper-ultrafast spectrum clustering tool based on #HyperdimensionalComputing! ⚡

This was a fun collaboration with the Rosing lab at UC San Diego, who are wizards in using advanced hardware to optimize complex computations.

OA paper: https://pubs.acs.org/doi/10.1021/acs.jproteome.2c00612

Clojure Conj talk by @gigasquid on Vector Symbolic Architectures is up: https://www.youtube.com/watch?v=ByzaFEVlaq

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #clojure

Clojure Conj talk by @gigasquid on Vector Symbolic Architectures is up: https://www.youtube.com/watch?v=ByzaFEVlaq

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #clojure

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

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

@hosford42 I'd be interested to see a description of what you've done for reinforcement learning with hyperdimensional computing.

#HDC #HyperdimensionalComputing #VSA #VectorSymbolicArchitecture

@hosford42 I'd be interested to see a description of what you've done for reinforcement learning with hyperdimensional computing.

#HDC #HyperdimensionalComputing #VSA #VectorSymbolicArchitecture

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

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

Antonello Rosato has organised a half-day workshop on Vector Symbolic Architectures / Hyperdimensional Computing, to be held in Antwerp, Belgium, as part of the Design, Automation and Test in Europe Conference (DATE23). The details are on LinkedIn (I'm really sorry about that):
https://www.linkedin.com/posts/rossgayler_log-in-to-easychair-activity-7019452856017539072-69GB?utm_source=share&utm_medium=member_desktop
#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing

@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

@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

@matspike Focusing on your final couple of points: linguistics needs structural representation & PDEs (continuous maths models) offer nothing for structure - You might want to take a look at Hyperdimensional Computing (HDC) / Vector Symbolic Architectures (VSA), which are all about how to represent and manipulate composite structures (trees, graphs, etc.) by simple arithmetic on high dimensional vector spaces (as a model of, say, the firing rates of a large group of neurons). Mostly it's algebraic, but PDEs are optional if you wanted to model the dynamics of a VSA/HDC system.

Early VSA paper referring to the Jackendoff example you use: https://arxiv.org/abs/cs/0412059

Me droning on about VSA as analogue computing for discrete structures: https://archive.org/details/Redwood_Center_2013_06_14_Ross_Gayler

A recent survey of the topic: https://arxiv.org/abs/2111.06077

#VSA #HDC
#VectorSymbolicArchitecture
#HyperdimensionalComputing