近日，美国加州大学教授Marcelo G. Mattar及其研究组揭示了用微小的循环神经网络发现认知策略。这一研究成果于2025年7月2日发表在国际顶尖学术期刊《自然》上。

在这里，该课题组人员提出了一种新的建模方法，利用递归神经网络来发现控制生物决策的认知算法。课题组研究人员表明，在预测个体动物和人类的选择方面，具有1到4个单元的神经网络通常优于经典认知模型，并与更大的神经网络相匹配，这些神经网络跨越了6个经过充分研究的奖励学习任务。关键的是，研究人员可以解释训练后的网络主题动态系统概念，使认知模型的统一比较和揭示选择行为的详细机制。他们的方法还估计了行为的维度，并对元强化学习人工智能代理学习的算法提供了见解。总的来说，研究小组提出了一种系统的方法来发现决策中可解释的认知策略，为神经机制提供了见解，并为研究健康和功能失调的认知奠定了基础。

研究人员表示，了解动物和人类如何从经验中学习并做出适应性决策是神经科学和心理学的一个基本目标。规范的建模框架，如贝叶斯推理和强化学习，为控制适应性行为的原则提供了有价值的见解。然而，这些框架的简单性往往限制了它们捕捉现实生物行为的能力，导致人工调整的循环，这容易导致研究人员的主观性。

附：英文原文

Title: Discovering cognitive strategies with tiny recurrent neural networks

Author: Ji-An, Li, Benna, Marcus K., Mattar, Marcelo G.

Issue&Volume: 2025-07-02

Abstract: Understanding how animals and humans learn from experience to make adaptive decisions is a fundamental goal of neuroscience and psychology. Normative modelling frameworks such as Bayesian inference1 and reinforcement learning2 provide valuable insights into the principles governing adaptive behaviour. However, the simplicity of these frameworks often limits their ability to capture realistic biological behaviour, leading to cycles of handcrafted adjustments that are prone to researcher subjectivity. Here we present a novel modelling approach that leverages recurrent neural networks to discover the cognitive algorithms governing biological decision-making. We show that neural networks with just one to four units often outperform classical cognitive models and match larger neural networks in predicting the choices of individual animals and humans, across six well-studied reward-learning tasks. Critically, we can interpret the trained networks using dynamical systems concepts, enabling a unified comparison of cognitive models and revealing detailed mechanisms underlying choice behaviour. Our approach also estimates the dimensionality of behaviour3 and offers insights into algorithms learned by meta-reinforcement learning artificial intelligence agents. Overall, we present a systematic approach for discovering interpretable cognitive strategies in decision-making, offering insights into neural mechanisms and a foundation for studying healthy and dysfunctional cognition.

DOI: 10.1038/s41586-025-09142-4

Source: https://www.nature.com/articles/s41586-025-09142-4