% 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},
}