Predicate learning in neural systems: Discovering latent generative structures

TL;DR

This paper demonstrates how neural networks can learn, combine, and extrapolate latent predicate structures from unstructured data, shedding light on the neural basis of complex human behaviors.

Contribution

It introduces a neural mechanism for learning and composing predicates from raw data, integrating neural oscillations for generative extrapolation.

Findings

Neural networks can learn predicates from unstructured data.

Predicates can be combined compositionally using neural oscillations.

The model achieves human-like extrapolation and generalization.

Abstract

Humans learn complex latent structures from their environments (e.g., natural language, mathematics, music, social hierarchies). In cognitive science and cognitive neuroscience, models that infer higher-order structures from sensory or first-order representations have been proposed to account for the complexity and flexibility of human behavior. But how do the structures that these models invoke arise in neural systems in the first place? To answer this question, we explain how a system can learn latent representational structures (i.e., predicates) from experience with wholly unstructured data. During the process of predicate learning, an artificial neural network exploits the naturally occurring dynamic properties of distributed computing across neuronal assemblies in order to learn predicates, but also to combine them compositionally, two computational aspects which appear to be necessary for human behavior as per formal theories in multiple domains. We describe how predicates can be combined generatively using neural oscillations to achieve human-like extrapolation and compositionality in an artificial neural network. The ability to learn predicates from experience, to represent structures compositionally, and to extrapolate to unseen data offers an inroads to understanding and modeling the most complex human behaviors.