Overcoming the Weight Transport Problem via Spike-Timing-Dependent Weight Inference
Neurons, Behavior, Data analysis, and Theory · 2021
DOI: 10.51628/001c.27423 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurons, Behavior, Data analysis, and Theory, 2021. Verfasst von Nasir Ahmad und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We propose a solution to the weight transport problem, which questions the biological plausibility of the backpropagation algorithm. We derive our method based upon a theoretical analysis of the (approximate) dynamics of leaky integrate-and-fire neurons. Our results demonstrate that the use of spike timing alone outcompetes existing biologically plausible methods for synaptic weight inference in spiking neural network models. Furthermore, our proposed method is more flexible, being applicable to any spiking neuron model, is conservative in how many parameters are required for implementation and can be deployed in an online-fashion with minimal computational overhead. These features, together with its biological plausibility, make it an attractive mechanism for weight inference at single synapses.
Zitieren
APA
Ahmad, N., Ambrogioni, L., & Gerven, M. A. J. V. (2021). Overcoming the Weight Transport Problem via Spike-Timing-Dependent Weight Inference. Neurons, Behavior, Data analysis, and Theory. https://doi.org/10.51628/001c.27423
Vancouver
Ahmad N, Ambrogioni L, Gerven MAJV. Overcoming the Weight Transport Problem via Spike-Timing-Dependent Weight Inference. Neurons, Behavior, Data analysis, and Theory. 2021. doi:10.51628/001c.27423
BibTeX
@article{Ahmad2021,
author = {Ahmad, Nasir and Ambrogioni, Luca and Gerven, Marcel A. J. van},
title = {Overcoming the Weight Transport Problem via Spike-Timing-Dependent Weight Inference},
journal = {Neurons, Behavior, Data analysis, and Theory},
year = {2021},
doi = {10.51628/001c.27423}
}
EUVIMED