activity
20172023
most citedA Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges

147 citations · 596 across the 21 of their papers we have counts for

collaborators

25 papers

cs.CV2023

Factorizers for Distributed Sparse Block Codes

Michael Hersche, Aleksandar Terzic, Geethan Karunaratne +6

Distributed sparse block codes (SBCs) exhibit compact representations for encoding and manipulating symbolic data structures using fixed-width vectors. One major challenge however…

cs.DC2023★ 7 cited

WHYPE: A Scale-Out Architecture with Wireless Over-the-Air Majority for Scalable In-memory Hyperdimensional Computing

Robert Guirado, Abbas Rahimi, Geethan Karunaratne +3

Hyperdimensional computing (HDC) is an emerging computing paradigm that represents, manipulates, and communicates data using long random vectors known as hypervectors. Among differ…

cs.ET2022★ 31 cited

In-memory factorization of holographic perceptual representations

Jovin Langenegger, Geethan Karunaratne, Michael Hersche +3

Disentanglement of constituent factors of a sensory signal is central to perception and cognition and hence is a critical task for future artificial intelligence systems. In this p…

cs.AR2022

Wireless On-Chip Communications for Scalable In-memory Hyperdimensional Computing

Robert Guirado, Abbas Rahimi, Geethan Karunaratne +3

Hyperdimensional computing (HDC) is an emerging computing paradigm that represents, manipulates, and communicates data using very long random vectors (aka hypervectors). Among diff…

cs.CV2022

Constrained Few-shot Class-incremental Learning

Michael Hersche, Geethan Karunaratne, Giovanni Cherubini +3

Continually learning new classes from fresh data without forgetting previous knowledge of old classes is a very challenging research problem. Moreover, it is imperative that such l…

cs.LG2022★ 9 cited

Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented Networks

Denis Kleyko, Geethan Karunaratne, Jan M. Rabaey +2

Memory-augmented neural networks enhance a neural network with an external key-value memory whose complexity is typically dominated by the number of support vectors in the key memo…