AIは1つしか学習しないのに関連概念を理解できるのか?(Can AI Grasp Related Concepts After Learning Only One?)


2023-10-25 ニューヨーク大学 (NYU)

◆研究者は、機械学習モデルに人間のような概念の学習と構成的な一般化能力を提供するMeta-learning for Compositionality(MLC)と呼ばれる新しい手法を開発しました。


メタ学習ニューラルネットワークによる人間のような体系的汎化 Human-like systematic generalization through a meta-learning neural network

Brenden M. Lake &Marco Baroni
Nature  Published:25 October 2023

figure 1


The power of human language and thought arises from systematic compositionality—the algebraic ability to understand and produce novel combinations from known components. Fodor and Pylyshyn1 famously argued that artificial neural networks lack this capacity and are therefore not viable models of the mind. Neural networks have advanced considerably in the years since, yet the systematicity challenge persists. Here we successfully address Fodor and Pylyshyn’s challenge by providing evidence that neural networks can achieve human-like systematicity when optimized for their compositional skills. To do so, we introduce the meta-learning for compositionality (MLC) approach for guiding training through a dynamic stream of compositional tasks. To compare humans and machines, we conducted human behavioural experiments using an instruction learning paradigm. After considering seven different models, we found that, in contrast to perfectly systematic but rigid probabilistic symbolic models, and perfectly flexible but unsystematic neural networks, only MLC achieves both the systematicity and flexibility needed for human-like generalization. MLC also advances the compositional skills of machine learning systems in several systematic generalization benchmarks. Our results show how a standard neural network architecture, optimized for its compositional skills, can mimic human systematic generalization in a head-to-head comparison.