Neuro Computing Systems - Translation and Scale Invariance for

Journal article

Jens Egholm Pedersen, Raghav Singhal, J. Conradt
Neuro Inspired Computational Elements Workshop, 2023

Cite

APA Click to copy
Pedersen, J. E., Singhal, R., & Conradt, J. (2023). Translation and Scale Invariance for Event-Based Object tracking. Neuro Inspired Computational Elements Workshop.

Chicago/Turabian Click to copy
Pedersen, Jens Egholm, Raghav Singhal, and J. Conradt. “Translation and Scale Invariance for Event-Based Object Tracking.” Neuro Inspired Computational Elements Workshop (2023).

MLA Click to copy
Pedersen, Jens Egholm, et al. “Translation and Scale Invariance for Event-Based Object Tracking.” Neuro Inspired Computational Elements Workshop, 2023.

BibTeX Click to copy

@article{jens2023a,
  title = {Translation and Scale Invariance for Event-Based Object tracking},
  year = {2023},
  journal = {Neuro Inspired Computational Elements Workshop},
  author = {Pedersen, Jens Egholm and Singhal, Raghav and Conradt, J.}
}

Abstract

Without temporal averaging, such as rate codes, it remains challenging to train spiking neural networks for temporal regression tasks. In this work, we present a novel method to accurately predict spatial coordinates from event data with a fully spiking convolutional neural network (SCNN) without temporal averaging. Our method performs on-par with artificial neural networks (ANN) of similar complexity. Additionally, we demonstrate faster convergence in half the time using translation- and scale-invariant receptive fields. To permit comparison with conventional frame-based ANNs, we base our results on a simulated event-based dataset with an unrealistic high density. Therefore, we hypothesize that our method significantly outperform ANNs in settings with lower event density, as seen in real-life event-based data. Our model is fully spiking and can be ported directly to neuromorphic hardware.