Synaptic plasticity as Bayesian inference

By Laurence Aitchison, Jannes Jegminat, J. Menendez, Jean-Pascal Pfister, Alexandre Pouget, Peter E. Latham. 2021

48 citations recorded by the source corpus.

Learning, especially rapid learning, is critical for survival. However, learning is hard; a large number of synaptic weights must be set based on noisy, often ambiguous, sensory information. In such a high-noise regime, keeping track of probability distributions over weights is the optimal strategy. Here we hypothesize that synapses take that strategy; in essence, when they estimate weights, they include error bars. They then use that uncertainty to adjust their learning rates, with more uncertain weights having higher learning rates. We also make a second, independent, hypothesis: synapses communicate their uncertainty by linking it to variability in postsynaptic potential size, with more uncertainty leading to more variability. These two hypotheses cast synaptic plasticity as a problem of Bayesian inference, and thus provide a normative view of learning. They generalize known learning rules, offer an explanation for the large variability in the size of postsynaptic potentials and make falsifiable experimental predictions. We propose that synapses compute probability distributions over weights, not just point estimates. Using probabilistic inference, we derive a new set of synaptic learning rules and show that they speed up learning in neural networks.

Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

  1. Frederik Benzing

In Electrical and Electronic Engineering

  1. Angelika Steger
  2. Frederik Benzing

Citations in the corpus