NCNEMay 17, 2017

Approximate Bayesian inference as a gauge theory

arXiv:1705.06614v21 citations
Originality Incremental advance
AI Analysis

This work addresses foundational challenges in modeling biological phenomena like attention and perception, but it is incremental as it builds on prior gauge theory proposals.

The paper tackles the problem of formalizing brain and biological systems as gauge theories for uncertainty resolution, proposing an algorithm using Schild's ladder for parallel transport of statistics on manifolds to enable variational inference.

In a published paper [Sengupta, 2016], we have proposed that the brain (and other self-organized biological and artificial systems) can be characterized via the mathematical apparatus of a gauge theory. The picture that emerges from this approach suggests that any biological system (from a neuron to an organism) can be cast as resolving uncertainty about its external milieu, either by changing its internal states or its relationship to the environment. Using formal arguments, we have shown that a gauge theory for neuronal dynamics -- based on approximate Bayesian inference -- has the potential to shed new light on phenomena that have thus far eluded a formal description, such as attention and the link between action and perception. Here, we describe the technical apparatus that enables such a variational inference on manifolds. Particularly, the novel contribution of this paper is an algorithm that utlizes a Schild's ladder for parallel transport of sufficient statistics (means, covariances, etc.) on a statistical manifold.

Foundations

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

Your Notes