Makkeh Abdullah, Graetz Marcel, Schneider Andreas C, Ehrlich David A, Priesemann Viola, Wibral Michael
Department of Data-driven Analysis of Biological Networks, Göttingen Campus Institute for Dynamics of Biological Networks, University of Göttingen, Göttingen 37077, Germany.
Complex Systems Theory, Max Planck Institute for Dynamics and Self-Organization, Göttingen 37077, Germany.
Proc Natl Acad Sci U S A. 2025 Mar 11;122(10):e2408125122. doi: 10.1073/pnas.2408125122. Epub 2025 Mar 5.
Despite the impressive performance of biological and artificial networks, an intuitive understanding of how their local learning dynamics contribute to network-level task solutions remains a challenge to this date. Efforts to bring learning to a more local scale indeed lead to valuable insights, however, a general constructive approach to describe local learning goals that is both interpretable and adaptable across diverse tasks is still missing. We have previously formulated a local information processing goal that is highly adaptable and interpretable for a model neuron with compartmental structure. Building on recent advances in Partial Information Decomposition (PID), we here derive a corresponding parametric local learning rule, which allows us to introduce "infomorphic" neural networks. We demonstrate the versatility of these networks to perform tasks from supervised, unsupervised, and memory learning. By leveraging the interpretable nature of the PID framework, infomorphic networks represent a valuable tool to advance our understanding of the intricate structure of local learning.
尽管生物网络和人工网络表现出色，但迄今为止，直观理解它们的局部学习动态如何促成网络层面的任务解决方案仍是一项挑战。将学习带到更局部尺度的努力确实带来了有价值的见解，然而，一种既具有可解释性又能适用于各种不同任务的描述局部学习目标的通用建设性方法仍然缺失。我们之前为具有隔室结构的模型神经元制定了一个高度可适应且可解释的局部信息处理目标。基于部分信息分解（PID）的最新进展，我们在此推导出一个相应的参数化局部学习规则，这使我们能够引入“信息同构”神经网络。我们展示了这些网络在执行监督学习、无监督学习和记忆学习任务方面的通用性。通过利用PID框架的可解释性，信息同构网络是推进我们对局部学习复杂结构理解的宝贵工具。
