Decomposed Inductive Procedure Learning: Learning Academic Tasks with Human-Like Data Efficiency

TL;DR

This paper demonstrates that decomposing learning into multiple specialized mechanisms significantly enhances data efficiency in AI, aligning it more closely with human learning, and highlights the importance of such decomposition over purely symbolic or subsymbolic approaches.

Contribution

The study introduces a multi-mechanism learning approach that improves data efficiency, showing that combining distinct learning mechanisms surpasses traditional single-mechanism models.

Findings

Decomposing learning mechanisms improves data efficiency to human-like levels.

Multiple mechanisms outperform symbolic or subsymbolic learning alone.

Integration of mechanisms is more impactful than mechanism type alone.

Abstract

Human learning relies on specialization -- distinct cognitive mechanisms working together to enable rapid learning. In contrast, most modern neural networks rely on a single mechanism: gradient descent over an objective function. This raises the question: might human learners' relatively rapid learning from just tens of examples instead of tens of thousands in data-driven deep learning arise from our ability to use multiple specialized mechanisms of learning in combination? We investigate this question through an ablation analysis of inductive human learning simulations in online tutoring environments. Comparing reinforcement learning to a more data-efficient 3-mechanism symbolic rule induction approach, we find that decomposing learning into multiple distinct mechanisms significantly improves data efficiency, bringing it in line with human learning. Furthermore, we show that this decomposition has a greater impact on efficiency than the distinction between symbolic and subsymbolic learning alone. Efforts to align data-driven machine learning with human learning often overlook the stark difference in learning efficiency. Our findings suggest that integrating multiple specialized learning mechanisms may be key to bridging this gap.