NCAIApr 29, 2019

Generative models as parsimonious descriptions of sensorimotor loops

arXiv:1904.12937v1149 citations
Originality Incremental advance
AI Analysis

This reframes generative models in neuroscience and AI from perceptual accuracy to behavioral utility, potentially impacting theories like the Bayesian brain.

The paper challenges the assumption that generative models must accurately represent the environment, proposing instead that they should describe sensorimotor relationships relevant for behavior.

The Bayesian brain hypothesis, predictive processing and variational free energy minimisation are typically used to describe perceptual processes based on accurate generative models of the world. However, generative models need not be veridical representations of the environment. We suggest that they can (and should) be used to describe sensorimotor relationships relevant for behaviour rather than precise accounts of the world.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes