这篇论文为需要可靠不确定性估计的连续时间序列建模场景提供了新思路，做概率机器学习或自动驾驶感知的团队可以关注其神经元级可解释性带来的调试优势。
论文提出了一种名为 Neuronal Stochastic Attention Circuit (NSAC) 的新型连续时间注意力架构，受线虫神经回路启发，将注意力 logit 计算建模为 Ornstein-Uhlenbeck 随机微分方程的解。该方法通过引入高斯分布到 logits，并利用 logistic-normal 分布传播随机性，实现了对注意力权重的概率化输出。NSAC 结合了高斯负对数似然和认知分离正则化器，能够联合量化偶然不确定性和认知不确定性。实验表明，NSAC 在连续时间函数逼近、多变量回归、长程预测、工业4.0和自动驾驶车道保持等任务中，在保持准确性的同时，提供了校准良好的不确定性估计，并具有神经元级别的可解释性。
Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning
Reliable quantification of uncertainty estimates in continuous-time (CT) representation learning remains nascent, particularly within CT attention architectures. We introduce the Neuronal Stochastic Attention Circuit (NSAC), a novel biologically-inspired CT attention architecture that reformulates attention logit computation as the solution of an Ornstein-Uhlenbeck stochastic differential equation modulated by input-dependent, nonlinear interlinked gates derived from repurposed C.elegans Neuronal Circuit Policies (NCPs) wiring mechanism. It induces Gaussian distribution over logits that propagates principled stochasticity through logistic-normal distribution over attention weights to yield probabilistic output. A two-term objective function combining Gaussian negative log-likelihood with an epistemic-separation regularizer enforces higher predictive variance and enables joint quantification of aleatoric and epistemic uncertainty. Empirically, we implement NSAC in a diverse set of learning tasks including: (i) irregular CT function approximation; (ii) multivariate regression; (iii) long-range forecasting; (iv) Industry 4.0; and (v) the lane-keeping of autonomous vehicles. We observe that the NSAC remains competitive against several baselines in terms of accuracy and produces reasonably well-calibrated uncertainty estimates while being interpretable at the neuronal cell level.