% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Renner:1028218,
author = {Renner, Alpha and Supic, Lazar and Danielescu, Andreea and
Indiveri, Giacomo and Olshausen, Bruno A. and Sandamirskaya,
Yulia and Sommer, Friedrich T. and Frady, E. Paxon},
title = {{N}euromorphic visual scene understanding with resonator
networks},
journal = {Nature machine intelligence},
volume = {6},
number = {6},
issn = {2522-5839},
address = {London},
publisher = {Springer Nature Publishing},
reportid = {FZJ-2024-04412},
pages = {641–652},
year = {2024},
abstract = {Analysing a visual scene by inferring the configuration of
a generative model is widely considered the most flexible
and generalizable approach to scene understanding. Yet, one
major problem is the computational challenge of the
inference procedure, involving a combinatorial search across
object identities and poses. Here we propose a neuromorphic
solution exploiting three key concepts: (1) a computational
framework based on vector symbolic architectures (VSAs) with
complex-valued vectors, (2) the design of hierarchical
resonator networks to factorize the non-commutative
transforms translation and rotation in visual scenes and (3)
the design of a multi-compartment spiking phasor neuron
model for implementing complex-valued resonator networks on
neuromorphic hardware. The VSA framework uses vector binding
operations to form a generative image model in which binding
acts as the equivariant operation for geometric
transformations. A scene can therefore be described as a sum
of vector products, which can then be efficiently factorized
by a resonator network to infer objects and their poses. The
hierarchical resonator network features a partitioned
architecture in which vector binding is equivariant for
horizontal and vertical translation within one partition and
for rotation and scaling within the other partition. The
spiking neuron model allows mapping the resonator network
onto efficient and low-power neuromorphic hardware. Our
approach is demonstrated on synthetic scenes composed of
simple two-dimensional shapes undergoing rigid geometric
transformations and colour changes. A companion paper
demonstrates the same approach in real-world application
scenarios for machine vision and robotics.},
cin = {PGI-15},
ddc = {004},
cid = {I:(DE-Juel1)PGI-15-20210701},
pnm = {5234 - Emerging NC Architectures (POF4-523)},
pid = {G:(DE-HGF)POF4-5234},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001258009300001},
doi = {10.1038/s42256-024-00848-0},
url = {https://juser.fz-juelich.de/record/1028218},
}