Fast Concept Mapping: The Emergence of Human Abilities in Artificial Neural Networks when Learning Embodied and Self-Supervised

TL;DR

This paper presents a method enabling artificial agents to learn semantic concepts rapidly through self-supervised exploration, mimicking human fast mapping, and achieving object recognition with minimal labeled data.

Contribution

Introduces fast concept mapping, a novel approach that uses neural firing patterns to associate concepts with very few labeled examples after self-supervised learning.

Findings

Objects identified with as little as one labeled example

Self-supervised embodiment leads to high-quality concept representations

Method mimics human fast mapping in neural networks

Abstract

Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large data sets of labeled examples but also very different from how humans learn. We introduce a setup in which an artificial agent first learns in a simulated world through self-supervised exploration. Following this, the representations learned through interaction with the world can be used to associate semantic concepts such as different types of doors. To do this, we use a method we call fast concept mapping which uses correlated firing patterns of neurons to define and detect semantic concepts. This association works instantaneous with very few labeled examples, similar to what we observe in humans in a phenomenon called fast mapping. Strikingly, this method already identifies objects with as little as one labeled example which highlights the quality of the encoding learned self-supervised through embodiment using curiosity-driven exploration. It therefor presents a feasible strategy for learning concepts without much supervision and shows that through pure interaction with the world meaningful representations of an environment can be learned.