Towards a more flexible Language of Thought: Bayesian grammar updates after each concept exposure

TL;DR

This paper demonstrates that humans can rapidly adapt their symbolic language of thought by creating new symbols through frequent use, and models this plasticity with a Bayesian updating framework.

Contribution

It introduces a Bayesian model capturing how humans update their language of thought by compiling frequently used expressions into new symbols, showing the system's plasticity.

Findings

Humans can quickly modify their symbolic language based on experience.

A Bayesian agent accurately predicts concept learning times.

Symbol creation is driven by usefulness in compressing concepts.

Abstract

Recent approaches to human concept learning have successfully combined the power of symbolic, infinitely productive rule systems and statistical learning to explain our ability to learn new concepts from just a few examples. The aim of most of these studies is to reveal the underlying language structuring these representations and providing a general substrate for thought. However, describing a model of thought that is fixed once trained is against the extensive literature that shows how experience shapes concept learning. Here, we ask about the plasticity of these symbolic descriptive languages. We perform a concept learning experiment that demonstrates that humans can change very rapidly the repertoire of symbols they use to identify concepts, by compiling expressions which are frequently used into new symbols of the language. The pattern of concept learning times is accurately described by a Bayesian agent that rationally updates the probability of compiling a new expression according to how useful it has been to compress concepts so far. By portraying the Language of Thought as a flexible system of rules, we also highlight the difficulties to pin it down empirically.