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

Maths/CogSci/MathPsych lazyweb: Are there any algebras in which you have subtraction but don't have negative values? Pointers appreciated. I am hoping that the abstract maths might shed some light on a problem in cognitive modelling.

The context is that I am interested in formal models of cognitive representations and I want to represent things (e.g. cats), don't believe that we should be able to represent negated things (i.e. I don't think it should be able to represent anti-cats), but it makes sense to subtract representations (e.g. remove the representation of a cat from the representation of a cat and a dog, leaving only the representation of the dog).

This *might* also be related to non-negative factorisation: (https://en.wikipedia.org/wiki/Non-negative_matrix_factorization) in that we want to represent a situation in terms of parts and don't allow anti-parts.

#mathematics #algebra #AbstractAlgebra #CogSci @cogsci #CognitiveScience #MathPsych #MathematicalPsychology

Most of the Artificial Neural Net simulation research I have seen (say, at venues like NeurIPS) seems to take a *very* simple conceptual approach to analysis of simulation results - just treat everything as independent observations with fixed effects conditions, when it might be better conceptualised as random effects and repeated measures. Do other people think this? Does anyone have views on whether it would be worthwhile doing more complex analyses and whether the typical publication venues would accept those more complex analyses? Are there any guides to appropriate analyses for simulation results, e.g what to do with the results coming from multi-fold cross-validation (I presume the results are not independent across folds because they share cases).

@cogsci #CogSci #CognitiveScience #MathPsych #MathematicalPsychology #NeuralNetworks #MachineLearning

@ereinbergs
tagging #MathPsych

New preprint:
“Algebras of actions in an agent’s representations of the world”

https://scholar.social/@E_Mondragon/111177742052625126

Here is a new version of our tutorial on fitting joint models of M/EEG and behavior! This version is much improved to the previous one due to a ton of additional work by co-author Kianté Fernandez as well as helpful reviewer comments.
https://psyarxiv.com/vf6t5

#eeg @eeg #cognition #MathPsych

See also the associated R package by Kianté here:
https://github.com/kiante-fernandez/Rhddmjags
Or the original Python scripts here:
https://github.com/mdnunez/pyhddmjags

Are you attending the conference of the Society for mathematical psychology/#ICCM/#EMPG 2023 in Amsterdam? Do you work with #ReactionTimes and/or #eeg?

Wait no more and subscribe to our #workshop on detecting the single trial processing stages in RTs using hidden semi-Markov Models!https://mathpsych.org/presentation/1128#/abstract

Not coming? Don't worry there will be other opportunities and you can always take a look at what we've built up to now : https://github.com/GWeindel/hsmm_mvpy

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

Hi maths-adjacent peeps, I have a maths notation question: Is there some conventional(ish) symbol for factorisation interpreted as a unary operator - e.g. F where F(x) returns a set of factors of x (but less dull and bland than F).

A quick, inept, internet search didn't find anything. I suspect there isn't a standard, conventional notation. I'm just looking for something I can use in a diagram that would look intuitively plausible as a symbol for factorisation.

I'll be presenting two pieces of research in the coming week:

(1) At #MathPsych Satellite Meeting: Self-Regulated Learning and Treatment Effect Heterogeneity: A Formal Model and Simulation (Thursday afternoon)

(2) At #Psynom22 I'll be giving a talk in the Metacognition II symposium entitled "Hidden Agenda-Based Regulation: Extending Models of
Study-Time Allocation to More Educationally Realistic
Stimuli" (Sunday morning)

Excited to meet new colleagues and see old friends @psynom22