An In-Silico Neural Model of Dynamic Routing Through Neuronal Coherence
Source: Stanford University
Authors describe a neurobiologically plausible model to implement dynamic routing using the concept of neuronal communication through neuronal coherence. The model has 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 realized by an appropriate alignment of the phases of their respective background oscillations by the routing control units. Authors present example architecture, implemented on a neuromorphic chip that is able to achieve circular-shift invariance. A simple extension to the model can accomplish circular-shift dynamic routing with only O(N) connections, compared to O(N2) connections required by traditional models.