行为延迟作为脑电反应时解码的弱事件时间监督
Behavioral Latency as Weak Event-Time Supervision for EEG Reaction-Time Decoding
浏览论文内容
中文总结 AI 辅助
该研究将试次级脑电反应时解码重新表述为事件时间后验建模，在5个随机种子下证实其相比标量回归等方法提升了预测性能，且具有可解释性。
中文摘要 AI 辅助
单试次脑电图（EEG）分析通常围绕事件和延迟展开，但基于EEG的反应时（RT）预测被设定为对固定刺激锁定窗口的标量回归。RT被视为窗口级标签，而非与反应相关动态的时间证据。本文将试次级RT解码重新表述为事件时间后验建模。模型不直接预测RT，而是估计与反应相关事件时间的后验分布$p(t_{\mathrm{event}}\mid X)$，并将其均值作为RT估计值，此过程将行为延迟视为与反应相关的潜在时间的弱观测。我们在Healthy Brain Network的对比度变化检测EEG任务上，采用被试不相交、释放分离的协议对该表述进行评估。在5个随机种子下，与标量回归和时间读出对照组相比，分布事件时间监督始终提升了保留数据的RT预测性能。受控客观比较表明，收益来源于事件时间分布的监督，而非仅基于期望的读出。架构对照显示，该效应在4种时间骨干网络中均存在，且与模型规模无关。除点预测外，后验几何特性可表征集中度、目标对齐和区间行为，而观测噪声校准可将潜在集中度与RT预测不确定性区分开。移位裁剪推理探究了捷径使用与时间定位的关系，匹配的移位抖动提升了鲁棒性，增加了平均灵敏度，并使预测更常沿预期的裁剪相对方向移动。灵敏度仍低于理想的裁剪相对定位，存在明显的等方差差距。综上，这些结果确立了事件时间后验建模是连接单试次EEG动态与行为时间的概率且可解释的表述。
英文摘要
Single-trial EEG analyses are often organized around events and latencies, yet EEG-based reaction-time (RT) prediction is posed as scalar regression on a fixed stimulus-locked window. RT is treated as a window-level label rather than timing evidence about response-relevant dynamics. Here we reformulate trial-wise RT decoding as event-time posterior modeling. Instead of predicting RT directly, the model estimates a posterior over response-relevant event times, $p(t_{\mathrm{event}}\mid X)$, and uses its mean as the RT estimate. This treats behavioral latency as a weak observation of latent response-relevant timing. We evaluate this formulation on the Healthy Brain Network contrast change detection EEG task under a subject-disjoint, release-separated protocol. Across five seeds, distributional event-time supervision consistently improves held-out RT prediction relative to scalar regression and temporal-readout controls. Controlled objective comparisons isolate supervision of the event-time distribution, rather than expectation-based readout alone, as the source of this gain. Architecture controls show that the effect persists across four temporal backbones and is not explained by model scale. Beyond point prediction, posterior geometry characterizes concentration, target alignment, and interval behavior, while observation-noise calibration separates latent concentration from predictive uncertainty over RT. Shifted-crop inference probes shortcut use versus temporal localization. Matched shift-jitter improves robustness, increases mean sensitivity, and moves predictions more often in the expected crop-relative direction. Sensitivity remains below ideal crop-relative localization, leaving a clear equivariance gap. Together, these results establish event-time posterior modeling as a probabilistic and interpretable formulation for linking single-trial EEG dynamics to behavioral timing.
发表机构
- Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）
- Hof University（霍夫大学）
- McGill University（麦吉尔大学）
- Carnegie Mellon University（卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。
