TY  - CONF
AU  - Renner, Alpha
AU  - Supic, Lazar
AU  - Danielescu, Andreea
AU  - Indiveri, Giacomo
AU  - Olshausen, Bruno A.
AU  - Sandamirskaya, Yulia
AU  - Sommer, Friedrich T.
AU  - Paxon Frady, E.
TI  - Neuromorphic Hyperdimensional Visual Scene Factorization
M1  - FZJ-2024-02523
PY  - 2023
AB  - In this talk at NNPC 2023, I will present a modular neuromorphic algorithm leveraging recent advancements in hyperdimensional computing/ Vector Symbolic Architectures (VSAs).VSAs have been proposed as a framework for symbolic reasoning, spatial, and graph operations on neuromorphic hardware. They make use of a small set of computational primitives that are robust, efficient, and compatible with diverse hardware. Our algorithm approaches scene understanding as a factorization problem and employs the resonator network to extract object identities and transformations. This is achieved by reflecting the algebraic structure of 2d rigid transforms (translations and rotation) in the neural VSA representation. Finally, we use a spike-timing-based implementation of phasor neurons to show an efficient proof of concept implementation on neuromorphic hardware and employ the model in a robotics task for visual odometry (visual SLAM).
T2  - International conference on neuromorphic, natural and physical computing
CY  - 25 Oct 2023 - 27 Oct 2023, Hannover (Germany)
Y2  - 25 Oct 2023 - 27 Oct 2023
M2  - Hannover, Germany
LB  - PUB:(DE-HGF)6
DO  - DOI:10.34734/FZJ-2024-02523
UR  - https://juser.fz-juelich.de/record/1024857
ER  -