An In-Silico Neural Model of Dynamic Routing Through Neuronal Coherence
Abstract
We describe a neurobiologically plausible model to implement dynamic routing using the concept of neuronal communication through neuronal coherence. The model has a three-tier architecture: a raw input tier, a routing control tier, and an invariant output tier. The correct mapping between input and output tiers is re- alized by an appropriate alignment of the phases of their respective background oscillations by the routing control units. We present an example architecture, im- plemented on a neuromorphic chip, that is able to achieve circular-shift invariance. A simple extension to our model can accomplish circular-shift dynamic routing with only O(N) connections, compared to O(N 2) connections required by tradi- tional models.
Cite
Text
Sridharan et al. "An In-Silico Neural Model of Dynamic Routing Through Neuronal Coherence." Neural Information Processing Systems, 2007.Markdown
[Sridharan et al. "An In-Silico Neural Model of Dynamic Routing Through Neuronal Coherence." Neural Information Processing Systems, 2007.](https://mlanthology.org/neurips/2007/sridharan2007neurips-insilico/)BibTeX
@inproceedings{sridharan2007neurips-insilico,
title = {{An In-Silico Neural Model of Dynamic Routing Through Neuronal Coherence}},
author = {Sridharan, Devarajan and Percival, Brian and Arthur, John and Boahen, Kwabena A.},
booktitle = {Neural Information Processing Systems},
year = {2007},
pages = {1401-1408},
url = {https://mlanthology.org/neurips/2007/sridharan2007neurips-insilico/}
}