Poster

The least-control principle for local learning at equilibrium

Alexander Meulemans · Nicolas Zucchet · Seijin Kobayashi · Johannes von Oswald · João Sacramento

Hall J #117

Keywords: [ meta learning ] [ Biologically-plausible learning ] [ local learning rules ] [ equilibrium recurrent neural networks ] [ predictive coding ] [ deep equilibrium models ] [ Neuroscience ] [ implicit models ] [ optimal control ]

[ Abstract ]
[ Paper [ Poster [ OpenReview
Wed 30 Nov 2 p.m. PST — 4 p.m. PST

Abstract:

Equilibrium systems are a powerful way to express neural computations. As special cases, they include models of great current interest in both neuroscience and machine learning, such as deep neural networks, equilibrium recurrent neural networks, deep equilibrium models, or meta-learning. Here, we present a new principle for learning such systems with a temporally- and spatially-local rule. Our principle casts learning as a \emph{least-control} problem, where we first introduce an optimal controller to lead the system towards a solution state, and then define learning as reducing the amount of control needed to reach such a state. We show that incorporating learning signals within a dynamics as an optimal control enables transmitting activity-dependent credit assignment information, avoids storing intermediate states in memory, and does not rely on infinitesimal learning signals. In practice, our principle leads to strong performance matching that of leading gradient-based learning methods when applied to an array of problems involving recurrent neural networks and meta-learning. Our results shed light on how the brain might learn and offer new ways of approaching a broad class of machine learning problems.

Chat is not available.