AI 中文总结
本研究提出用纯局部稳态可塑性调节深度神经网络全局动力学状态的方法，可将网络推向临界状态，抵消训练诱导的超临界漂移，揭示动力学调节与任务优化的竞争关系。
AI 中文摘要
深度神经网络是高维动力学系统，其功能依赖于活动与扰动在多层间的稳定传播，因此维持合适的动力学状态对鲁棒学习及防止训练过程中的动力学不稳定至关重要。本文表明，深度神经网络的全局动力学状态可通过纯局部的稳态可塑性自主调节：神经元活动由输入响应推断，单个突触仅利用其突触后神经元的活动进行增强或减弱。无需测量任何全局网络属性，该规则可将网络从亚临界和超临界初始条件推向共同的临界状态，其特征为活动传播守恒及有限时间最大李雅普诺夫指数消失。当与基于梯度的学习结合时，稳态适应性可抵消训练诱导的向超临界动力学的漂移，同时揭示动力学调节与任务优化间的竞争关系。本研究结果证明了自适应自组织如何在深度神经网络中实现，以及局部可塑性如何控制其集体动力学工作点。
英文摘要
Deep neural networks are high-dimensional dynamical systems whose function depends on the stable propagation of activity and perturbations across many layers. Maintaining suitable dynamical regimes may therefore be essential for robust learning and for preventing dynamical instabilities during training. Here, we show that the global dynamical state of a deep neural network can be autonomously regulated by purely local homeostatic plasticity. Neuronal activity is inferred from responses across inputs, and individual synapses are strengthened or weakened using only the activity of their postsynaptic neuron. Without measuring any global network property, this rule drives networks from both subcritical and supercritical initial conditions toward a common critical state, characterized by conserved activity propagation and a vanishing largest finite-time Lyapunov exponent. When combined with gradient-based learning, homeostatic adaptation counteracts the training-induced drift toward supercritical dynamics, while revealing a competition between dynamical regulation and task optimization. Our results demonstrate how adaptive self-organization can be implemented in deep neural networks and how local plasticity can control their collective dynamical operating point.
