Mastodawn

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

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

Approaching limitations of digital computing technologies have spurred research in neuromorphic and other unconventional approaches to computing. Here we argue that if we want to systematically engineer computing systems that are based on unconventional physical effects, we need guidance from a formal theory that is different from the symbolic-algorithmic theory of today's computer science textbooks. We propose a general strategy for developing such a theory, and within that general view, a specific approach that we call "fluent computing". In contrast to Turing, who modeled computing processes from a top-down perspective as symbolic reasoning, we adopt the scientific paradigm of physics and model physical computing systems bottom-up by formalizing what can ultimately be measured in any physical substrate. This leads to an understanding of computing as the structuring of processes, while classical models of computing systems describe the processing of structures.

arXiv.org

Ross Gayler Jan 26, 2025

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

Join our Cloud HD Video Meeting

Zoom is the leader in modern enterprise video communications, with an easy, reliable cloud platform for video and audio conferencing, chat, and webinars across mobile, desktop, and room systems. Zoom Rooms is the original software-based conference room solution used around the world in board, conference, huddle, and training rooms, as well as executive offices and classrooms. Founded in 2011, Zoom helps businesses and organizations bring their teams together in a frictionless environment to get more done. Zoom is a publicly traded company headquartered in San Jose, CA.

Zoom Video

Ross Gayler May 9, 2024

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

Hypervectors. AGI Event

Hypervectors AGI - Let's dive into the exciting world of artificial general intelligence together!

Eventbrite