Bayesian synaptic plasticity is energy efficient
James Malkin,Cian O'Donnell,Conor Houghton,Laurence Aitchison · COSYNE 2022
Recent work (Aitchison et al. 2021) suggests that synaptic plasticity performs Bayesian inference and that, moreover, variability in synaptic efficacy might reflect uncertainty in the synaptic weight. Here, we consider whether similar phenomena emerge merely from minimizing synapse energetic costs during learning. Following established biophysical principles, we assume that noisy synaptic transmission is energetically cheaper than precise transmission. However, stochastic synapses may be detrimental to performance because noisy transmission adds randomness to a neural network’s activity, and s
Fri, Mar 18, 2022