图神经网络可解耦复杂神经系统的结构与功能。
Graph neural networks uncover structure and functions underlying the activity of simulated neural assemblies
- 用图神经网络预测神经活动并分解为可解释成分。
- 在数千神经元模拟中同时揭示连接矩阵、神经类型与信号功能。
- 适合研究大型神经环路机制的科研人员使用。
训练图神经网络以预测可观测动态，可将复杂异质系统的时序活动分解为简单且可解释的表征。本文将该框架应用于包含数千个神经元的模拟神经集合，证明其能联合揭示连接矩阵、神经元类型、信号功能，甚至在某些情况下识别隐藏的外部刺激。相较于强调预测精度但解释性差的循环神经网络和Transformer等现有机器学习方法，本方法既能可靠预测神经活动，又能解释大规模神经集合的运作机制。
原文摘要 · Abstract (English)
Graph neural networks trained to predict observable dynamics can be used to decompose the temporal activity of complex heterogeneous systems into simple, interpretable representations. Here we apply this framework to simulated neural assemblies with thousands of neurons and demonstrate that it can jointly reveal the connectivity matrix, the neuron types, the signaling functions, and in some cases hidden external stimuli. In contrast to existing machine learning approaches such as recurrent neural networks and transformers, which emphasize predictive accuracy but offer limited interpretability, our method provides both reliable forecasts of neural activity and interpretable decomposition of the mechanisms governing large neural assemblies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。