Brain in the Dark: Design Principles for Neuro-mimetic Learning and Inference

TL;DR

This paper explores principles for designing neuro-mimetic generative models that enable the brain to perform inference and learning in darkness, focusing on model formulation, inversion, and the implications of mean field approximations.

Contribution

It provides a framework for designing brain-inspired generative models and analyzes the effects of different mean field approximations on variational inference.

Findings

Analysis of mean field approximation choices for variational inference

Guidelines for designing neuro-mimetic generative models

Insights into inference and learning in darkness

Abstract

Even though the brain operates in pure darkness, within the skull, it can infer the most likely causes of its sensory input. An approach to modelling this inference is to assume that the brain has a generative model of the world, which it can invert to infer the hidden causes behind its sensory stimuli, that is, perception. This assumption raises key questions: how to formulate the problem of designing brain-inspired generative models, how to invert them for the tasks of inference and learning, what is the appropriate loss function to be optimised, and, most importantly, what are the different choices of mean field approximation (MFA) and their implications for variational inference (VI).