美国Astera研究所Thomas Miconi等研究人员合作揭示，可塑性神经网络中关系学习和快速知识重组的神经机制。2025年1月15日，《自然—神经科学》杂志在线发表了这项成果。

研究人员报告了具有神经调节突触可塑性的神经网络（允许自我导向学习），通过人工元学习（学习如何学习）识别出能够执行传递推理和列表连接的网络，并且进一步表达了人类和动物中广泛观察到的行为模式。至关重要的是，只有采用“主动”解决方案的网络，在这种方案中，来自过去试验的项以重新编码的形式重新出现在神经活动中，才能进行列表连接。这些结果揭示了关系学习的完全神经机制，并突出了发现这些机制的方法。

据了解，人类和动物具有显著的能力，能够学习经验中项与项之间的关系（如刺激、物体和事件），从而实现结构化的泛化和快速同化新信息。这种关系学习的一个基本类型是顺序学习，它使得传递推理成为可能（如果A > B且B > C，那么A > C）以及列表连接（A > B > C和D > E > F在学习C > D后迅速“重组”为A > B > C > D > E > F）。尽管长期以来有很多研究，但传递推理和顺序知识的快速重组的神经生物学机制仍然难以捉摸。

附：英文原文

Title: Neural mechanisms of relational learning and fast knowledge reassembly in plastic neural networks

Author: Miconi, Thomas, Kay, Kenneth

Issue&Volume: 2025-01-15

Abstract: Humans and animals have a striking ability to learn relationships between items in experience (such as stimuli, objects and events), enabling structured generalization and rapid assimilation of new information. A fundamental type of such relational learning is order learning, which enables transitive inference (if A>B and B>C, then A>C) and list linking (A>B>C and D>E>F rapidly ‘reassembled’ into A>B>C>D>E>F upon learning C>D). Despite longstanding study, a neurobiologically plausible mechanism for transitive inference and rapid reassembly of order knowledge has remained elusive. Here we report that neural networks endowed with neuromodulated synaptic plasticity (allowing for self-directed learning) and identified through artificial metalearning (learning-to-learn) are able to perform both transitive inference and list linking and, further, express behavioral patterns widely observed in humans and animals. Crucially, only networks that adopt an ‘active’ solution, in which items from past trials are reinstated in neural activity in recoded form, are capable of list linking. These results identify fully neural mechanisms for relational learning, and highlight a method for discovering such mechanisms.

DOI: 10.1038/s41593-024-01852-8

Source: https://www.nature.com/articles/s41593-024-01852-8