通过人类和人工神经网络中的抽象表示的组合概括
Compositional generalization through abstract representations in human and artificial neural networks
摘要:
人类具有快速概括新任务的非凡能力,这在人工学习系统中很难重现。组合性被认为是支持人类泛化的一种关键机制,但其神经实现和对行为影响的证据仍然很少。在这里,我们研究的计算特性与合成泛化在人类和人工神经网络(ANN)的高度组成的任务。首先,我们使用全皮层功能性磁共振成像(fMRI)数据识别了人类成分泛化的行为特征及其神经相关性。接下来,我们设计了预训练范例,并通过一个我们称之为{ \em原语预训练}的过程来将组合任务元素赋予ANN。我们发现,具有这种先验知识的ANN与人类行为和神经成分特征有更好的对应性。重要的是,基元预训练诱导了抽象的内部表示、出色的zero-shot泛化和样本高效学习。此外,它还产生了一个与人类功能磁共振成像数据相匹配的抽象表征层次,其中感觉规则抽象出现在早期感觉区域,运动规则抽象出现在后来的运动区域。我们的研究结果提供了实证支持的组成概括在人类行为中的作用,牵连抽象表示作为其神经实现,并说明这些表示可以嵌入到人工神经网络通过设计简单而有效的预训练程序。
英文摘要:
Humans have a remarkable ability to rapidly generalize to new tasks that is difficult to reproduce in artificial learning systems. Compositionality has been proposed as a key mechanism supporting generalization in humans, but evidence of its neural implementation and impact on behavior is still scarce. Here we study the computational properties associated with compositional generalization in both humans and artificial neural networks (ANNs) on a highly compositional task. First, we identified behavioral signatures of compositional generalization in humans, along with their neural correlates using whole-cortex functional magnetic resonance imaging (fMRI) data. Next, we designed pretraining paradigms aided by a procedure we term {\em primitives pretraining} to endow compositional task elements into ANNs. We found that ANNs with this prior knowledge had greater correspondence with human behavior and neural compositional signatures. Importantly, primitives pretraining induced abstract internal representations, excellent zero-shot generalization, and sample-efficient learning. Moreover, it gave rise to a hierarchy of abstract representations that matched human fMRI data, where sensory rule abstractions emerged in early sensory areas, and motor rule abstractions emerged in later motor areas. Our findings give empirical support to the role of compositional generalization in human behavior, implicate abstract representations as its neural implementation, and illustrate that these representations can be embedded into ANNs by designing simple and efficient pretraining procedures.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。