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
#NewPaper #TheoreticalComputerScience #neuromorphic #CogSci #CognitiveScience #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #AnalogComputing
#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
#memristor #neuromorphic #vsa #vectorsymbolicarchitecture #HDC #hyperdimensionalcomputing
Dan's #illumos #zfs #HDC update:
People who've been following me know I've had 14TB drive problems, often manifesting as spontaneous power-cycles during disk-intensive ops (e.g. scrubs, backups). Most recent spate was attributed to one drive this time. It's now replaced, and it resilvered all 5.7TB w/o incident.
Next test coming soon: A full backup.
My working theories if it fails again:
- Case problems (replace the case).
- Cable problems (replace cables)
- Mobo problems (swap ports)
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
#vsa #vectorsymbolicarchitecture #HDC #hyperdimensionalcomputing #cogsci #cognitivescience #neuromorphic #unconventionalcomputing
Clojure Conj talk by @gigasquid on Vector Symbolic Architectures is up: https://www.youtube.com/watch?v=ByzaFEVlaq
#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #clojure
#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
#vsa #vectorsymbolicarchitecture #HDC #hyperdimensionalcomputing #cogrob #CognitiveRobotics #compcogsci #computationalcognitivescience #cogsci #cognitivescience #mathpsych #mathematicalpsychology
Lots of opportunities in #NorthYorkshire to use Hill Decent Control. #HDC is essentially a cruise control system that uses traction control technology with the anti-lock brakes - this then continually adjusts the braking pressure to help control slippage & maintain a constant preset speed #LandRover #AboveandBeyond
#northyorkshire #HDC #Landrover #aboveandbeyond
@hosford42 I'd be interested to see a description of what you've done for reinforcement learning with hyperdimensional computing.
#HDC #HyperdimensionalComputing #VSA #VectorSymbolicArchitecture
#HDC #hyperdimensionalcomputing #vsa #vectorsymbolicarchitecture
Over the weekend I threw together some #Python #TensorFlow code to use #HyperDimensionalComputing for #ReinforcementLearning. I was surprised to see my naive, first attempt blow away #DeepLearning. I'm hooked.
Where have you been all my life, #HDC?
#python #tensorflow #hyperdimensionalcomputing #reinforcementlearning #deeplearning #HDC
Here are two high level articles that mention Vector Symbolic Architecure / HyperDimensional Computing in the more "popular" end of the technical press:
https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10098176
#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CompCogSci #ComputationalCognitiveScience #CogSci #CognitiveScience #MathPsych #MathematicalPsychology
#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
#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
#vsa #vectorsymbolicarchitecture #HDC #hyperdimensionalcomputing
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
#cogsci #cognitivescience #compcogsci #computationalcognitivescience #vsa #vectorsymbolicarchitecture #HDC #hyperdimensionalcomputing
A blog post on basic Vector Symbolic Architecture / Hyperdimensional Computing operations implemented in Clojure (a dialect of LISP running on the JVM), written by Carin Meier (a star in the Clojure firmament).
http://gigasquid.github.io/blog/2022/12/31/vector-symbolic-architectures-in-clojure/
#VectorSymbolicArchitecture #VSA #HyperdimensionalComputing #HDC #cogsci #clojure
#vectorsymbolicarchitecture #vsa #hyperdimensionalcomputing #HDC #cogsci #clojure
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
#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
#vsa #vectorsymbolicarchitecture #HDC #hyperdimensionalcomputing #cogsci #cognitivescience #cogrob #CognitiveRobotics #mathpsych #compcogsci #compsci #computerscience #neuromorphic #job
Abstract:
Motivated by recent innovations in biologically inspired neuromorphic hardware, this article presents a novel unsupervised machine learning algorithm named Hyperseed that draws on the principles of vector symbolic architectures (VSAs) for fast learning of a topology preserving feature map of unlabeled data. It relies on two major operations of VSA, binding and bundling. The algorithmic part of Hyperseed is expressed within the Fourier holographic reduced representations (FHRR) model, which is specifically suited for implementation on spiking neuromorphic hardware. The two primary contributions of the Hyperseed algorithm are few-shot learning and a learning rule based on single vector operation. These properties are empirically evaluated on synthetic datasets and on illustrative benchmark use cases, IRIS classification, and a language identification task using the n -gram statistics. The results of these experiments confirm the capabilities of Hyperseed and its applications in neuromorphic hardware.
https://ieeexplore.ieee.org/abstract/document/9953974
#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CogSci #CogRob #MathPsych
#vsa #vectorsymbolicarchitecture #HDC #hyperdimensionalcomputing #cogsci #cogrob #mathpsych
@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
#vsa #HDC #vectorsymbolicarchitecture #hyperdimensionalcomputing
Editorial of a special issue on Hyperdimensional omputing (Vector Symbolic Architectures)
https://www.frontiersin.org/articles/10.3389/fnins.2022.1102568/full
#HyperdimensionalComputing #HDC #VectorSymbolicArchitecture #VSA #CogSci #neuromorphic
#hyperdimensionalcomputing #HDC #vectorsymbolicarchitecture #vsa #cogsci #neuromorphic
The Centre For Data Analytics and Cognition at La Trobe University and Luleå University of Technology ran a hybrid event in hyperdimensional computing (HDC) and its applications in Artificial Intelligence and neuromorphic systems, on 7 December 2022 . This event aimed to develop knowledge and skills in HDC, an unconventional computing technique, its algorithmic value in practical AI and data analytics solutions, and its potential in enabling novel brain-inspired (neuromorphic) computing technologies.
The event was recorded and is publicly available at the links below:
* Event announcement and program: https://lnkd.in/gNVkJD5q
* Video (3.2 hours): https://lnkd.in/gUf7zx9n
* Slides of Osipov talks: https://lnkd.in/gdV_Bd8A
In case you haven't come across hyperdimensional computing: Higher cognition strongly suggests that humans can represent and operate on complex, compositional data structures like trees and graphs. The problem then is how to represent and operate on those data structures in neural nets. Hyperdimensional computing is a mathematical model of computation in high dimensional vector spaces that allows complex, discrete computation to be readily mapped onto neural or neuromorphic implementation. If you're interested you might look at: https://lnkd.in/gzBSkUwH
#VSA #HDC #ArtificialIntelligence #neuromorphic
#VectorSymbolicArchitecture
#HyperdimensionalComputing
#AI #AGI #CogSci #CogRob #robotics
#vsa #HDC #artificialintelligence #neuromorphic #vectorsymbolicarchitecture #hyperdimensionalcomputing #ai #agi #cogsci #cogrob #robotics