脑动力学基础模型的扰动有效性：一项受控的概念验证模拟

中文摘要 AI 辅助

用于人脑记录的基础模型通常通过信号重建、未来状态预测以及向下游任务的迁移来评估。然而，这些基准并不能确定迁移后的模型在系统受到主动扰动时是否仍然有效。我们将扰动有效性定义为，在有限的系统特定适应之后，给定当前状态和受控输入条件下未来轨迹的条件分布得以保持的性质，并在三个层面进行评估：时间序列准确性、动力学结构相似性，以及对校准中未包含扰动的响应。我们在随机双稳态系统的预言机漂移模拟中演示了该框架。两个在其他方面相同的多层感知器分别在来自被动或输入驱动轨迹的漂移评估上进行了训练。接下来，对于每个留出系统，共享权重被冻结，仅适应一个三维嵌入，并以从头拟合的、设定正确的三次模型作为比较对象。通过两到五次系统特定评估，扰动预训练在恢复受控流、景观几何、有限运行占据率、响应分布和剂量-转变曲线方面产生了更低的误差。该优势在五次独立运行中得以重现，在被动模型的完整网络适应下依然存在，并且可归因于输入激励而非转变状态覆盖：仅激励一项就在五次运行中的五次里将受控流误差相对于仅覆盖降低了1.94倍。随着校准规模的增长，三次模型变得具有竞争力，表明该益处特定于少样本迁移。这项受控演示并未测试从含噪或部分观测的脑记录中恢复动力学。它表明，被动预测应辅以受控输入下的前瞻性评估。

英文摘要

Foundation models for human brain recordings are usually evaluated by signal reconstruction, future-state prediction, and transfer to downstream tasks. However, these benchmarks do not establish whether a transferred model remains valid when the system is actively perturbed. We define perturbational validity as the preservation, after limited system-specific adaptation, of the conditional distribution of future trajectories given the current state and a controlled input, and we evaluate it at three levels: time-series accuracy, dynamical-structure similarity, and responses to perturbations excluded from calibration. We demonstrate the framework in an oracle-drift simulation of stochastic bistable systems. Two otherwise identical multilayer perceptrons were trained on drift evaluations from passive or input-driven trajectories. Next, for each held-out system the shared weights were frozen and only a three-dimensional embedding was adapted, with a correctly specified cubic model fitted from scratch as comparator. With two to five system-specific evaluations, perturbational pretraining yielded lower errors in recovering controlled flow, landscape geometry, finite-run occupancy, response distributions, and dose-transition curves. The advantage was reproduced across five independent runs, persisted under full-network adaptation of the passive model, and was attributable to input excitation rather than transition-state coverage: excitation alone lowered controlled-flow error 1.94-fold relative to coverage alone, in five of five runs. The cubic model became competitive as calibration grew, showing that the benefit is specific to few-shot transfer. This controlled demonstration does not test recovery of dynamics from noisy or partially observed brain recordings. It shows why passive prediction should be complemented by prospective evaluation under controlled inputs.

发表机构

• Philipps-Universität Marburg（马尔堡菲利普大学）
• University of Münster（明斯特大学）

机构由 AI 辅助整理，请以论文原文为准。