School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China.
Sci Adv. 2024 Jul 26;10(30):eadm8430. doi: 10.1126/sciadv.adm8430.
Advances in artificial intelligence enable neural networks to learn a wide variety of tasks, yet our understanding of the learning dynamics of these networks remains limited. Here, we study the temporal dynamics during learning of Hebbian feedforward neural networks in tasks of continual familiarity detection. Drawing inspiration from network neuroscience, we examine the network's dynamic reconfiguration, focusing on how network modules evolve throughout learning. Through a comprehensive assessment involving metrics like network accuracy, modular flexibility, and distribution entropy across diverse learning modes, our approach reveals various previously unknown patterns of network reconfiguration. We find that the emergence of network modularity is a salient predictor of performance and that modularization strengthens with increasing flexibility throughout learning. These insights not only elucidate the nuanced interplay of network modularity, accuracy, and learning dynamics but also bridge our understanding of learning in artificial and biological agents.
人工智能的进步使得神经网络能够学习各种各样的任务，但我们对这些网络的学习动态的理解仍然有限。在这里，我们研究了在持续熟悉度检测任务中赫布前馈神经网络学习过程中的时间动态。受网络神经科学的启发，我们研究了网络的动态重新配置，重点关注网络模块在整个学习过程中的演变方式。通过涉及网络准确性、模块灵活性和在不同学习模式下的分布熵等指标的综合评估，我们的方法揭示了网络重新配置的各种以前未知的模式。我们发现，网络模块化的出现是性能的一个显著预测指标，并且模块化随着学习过程中灵活性的增加而增强。这些见解不仅阐明了网络模块化、准确性和学习动态之间的细微相互作用，还弥合了我们对人工和生物智能体学习的理解。
