Disentangling the attributes of a sensory signal is central to sensory perception and cognition and hence is a critical task for future artificial intelligence systems. Here we present a compute engine capable of efficiently factorizing high-dimensional holographic representations of combinations of such attributes, by exploiting the computation-in-superposition capability of brain-inspired hyperdimensional computing, and the intrinsic stochasticity associated with analogue in-memory computing based on nanoscale memristive devices. Such an iterative in-memory factorizer is shown to solve at least five orders of magnitude larger problems that cannot be solved otherwise, as well as substantially lowering the computational time and space complexity. We present a large-scale experimental demonstration of the factorizer by employing two in-memory compute chips based on phase-change memristive devices. The dominant matrix–vector multiplication operations take a constant time, irrespective of the size of the matrix, thus reducing the computational time complexity to merely the number of iterations. Moreover, we experimentally demonstrate the ability to reliably and efficiently factorize visual perceptual representations.

Langenegger, J., Karunaratne, G., Hersche, M., Benini, L., Sebastian, A., Rahimi, A. (2023). In-memory factorization of holographic perceptual representations. NATURE NANOTECHNOLOGY, 18(5), 479-485 [10.1038/s41565-023-01357-8].

In-memory factorization of holographic perceptual representations

Benini, Luca;
2023

Abstract

Disentangling the attributes of a sensory signal is central to sensory perception and cognition and hence is a critical task for future artificial intelligence systems. Here we present a compute engine capable of efficiently factorizing high-dimensional holographic representations of combinations of such attributes, by exploiting the computation-in-superposition capability of brain-inspired hyperdimensional computing, and the intrinsic stochasticity associated with analogue in-memory computing based on nanoscale memristive devices. Such an iterative in-memory factorizer is shown to solve at least five orders of magnitude larger problems that cannot be solved otherwise, as well as substantially lowering the computational time and space complexity. We present a large-scale experimental demonstration of the factorizer by employing two in-memory compute chips based on phase-change memristive devices. The dominant matrix–vector multiplication operations take a constant time, irrespective of the size of the matrix, thus reducing the computational time complexity to merely the number of iterations. Moreover, we experimentally demonstrate the ability to reliably and efficiently factorize visual perceptual representations.
2023
Langenegger, J., Karunaratne, G., Hersche, M., Benini, L., Sebastian, A., Rahimi, A. (2023). In-memory factorization of holographic perceptual representations. NATURE NANOTECHNOLOGY, 18(5), 479-485 [10.1038/s41565-023-01357-8].
Langenegger, Jovin; Karunaratne, Geethan; Hersche, Michael; Benini, Luca; Sebastian, Abu; Rahimi, Abbas
File in questo prodotto:
File Dimensione Formato  
2211.05052v2.pdf

Open Access dal 01/10/2023

Tipo: Postprint / Author's Accepted Manuscript (AAM) - versione accettata per la pubblicazione dopo la peer-review
Licenza: Licenza per accesso libero gratuito
Dimensione 9.64 MB
Formato Adobe PDF
9.64 MB Adobe PDF Visualizza/Apri
41565_2023_1357_MOESM1_ESM.pdf

accesso aperto

Tipo: File Supplementare
Licenza: Licenza per accesso libero gratuito
Dimensione 1.39 MB
Formato Adobe PDF
1.39 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/963493
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 22
  • ???jsp.display-item.citation.isi??? 19
social impact