Synaptic Weight Distributions Depend on the Geometry of Plasticity

arXiv:2305.19394v2 Announce Type: replace-cross
Abstract: A growing literature in computational neuroscience leverages gradient descent and learning algorithms that approximate it to study synaptic plasticity in the brain. However, the vast majority of this work ignores a critical underlying assumption: the choice of distance for synaptic changes - i.e. the geometry of synaptic plasticity. Gradient descent assumes that the distance is Euclidean, but many other distances are possible, and there is no reason that biology necessarily uses Euclidean geometry. Here, using …

abstract algorithms arxiv brain computational computational neuroscience cs.lg cs.ne geometry gradient literature neuroscience q-bio.nc study type vast work