# Learning as the Unsupervised Alignment of Conceptual Systems

## TL;DR

This paper explores how conceptual systems can be aligned through unsupervised learning by leveraging unique signatures of concepts across different modalities, facilitating easier learning as more concepts are integrated.

## Contribution

It introduces a computational framework demonstrating that environmental information enables unsupervised alignment of conceptual systems, reducing reliance on explicit supervision.

## Key findings

- Concepts have unique signatures within systems.
- Alignment improves as more concepts are added.
- Children's early concepts form aligned systems.

## Abstract

Concept induction requires the extraction and naming of concepts from noisy perceptual experience. For supervised approaches, as the number of concepts grows, so does the number of required training examples. Philosophers, psychologists, and computer scientists, have long recognized that children can learn to label objects without being explicitly taught. In a series of computational experiments, we highlight how information in the environment can be used to build and align conceptual systems. Unlike supervised learning, the learning problem becomes easier the more concepts and systems there are to master. The key insight is that each concept has a unique signature within one conceptual system (e.g., images) that is recapitulated in other systems (e.g., text or audio). As predicted, children's early concepts form readily aligned systems.