脑电图(EEG) 是监测脑电活动的关键, 非侵入性方法。脑电图可以跨越几秒到几个小时,，由于两个主要因素，对现有深度学习方法构成了主要障碍: (1) 现有的脑电图模型主要建立在注意力机制上, 随着序列长度的增加而产生二次缩放, 和 (2) 由于固定长度输入要求，原始脑电图信号必须以滑动窗口方式处理, 阻碍了对整个信号的全局理解。在这个程度上,，我们提出 CaMBRAIN - 第一个基于因果, Mamba 的状态空间模型(SSM) 能够实时推断 EEG 信号, 认为，鉴于 EEG 的因果, 单向性质，双向方法不必要地昂贵。然而，, 训练这样的模型并非易事,，因为关键的脑电图事件可能非常短暂（不到一秒），但却被跨越几分钟的长间隔分开。当前的 EEG 方法使用针对信号重建进行优化的自监督目标,，但这些方法不太适合流式 SSM;，它们无法显式训练隐藏状态以保留流式推理所需的显着远程上下文。因此，我们引入了专门定制的多阶段自监督训练流程，以鼓励长期记忆保留和脑电图信号,的强大性能，同时保留状态空间模型的线性时间复杂度。 CaMBRAIN 在 3 个不同的 EEG 数据集上实现了最先进的 (SOTA) 结果，吞吐量比现有模型高 >10x,，从而实现第一个能够对可变长度 EEG 信号进行远程, 连续推理的模型。

Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to multiple hours, posing a major hurdle for existing deep learning methods due to two major factors: (1) existing EEG models are predominantly built upon the attention mechanism, incurring quadratic scaling as the sequence length increases, and (2) raw EEG signals must be processed in a sliding-window fashion due to fixed-length input requirements, preventing global understanding of the entire signal. To this extent, we propose CaMBRAIN - the first Causal, Mamba-based state space model (SSM) capable of real-time inference of EEG signals, arguing that bidirectional approaches are needlessly expensive given the causal, unidirectional nature of EEG. However, training such a model is non-trivial, as crucial EEG events can be extremely brief - within fractions of a second - yet separated by long intervals spanning minutes. Current EEG methods use self-supervised objectives that optimize for signal reconstruction, but these are not well suited for streaming SSMs; they fail to explicitly train the hidden state to retain the salient long-range context needed for streaming inference. We therefore introduce a multi-stage self-supervised training pipeline specifically tailored to encourage long-range memory retention and strong performance on EEG signals, while preserving the linear-time complexity of state space models. CaMBRAIN achieves state-of-the-art (SOTA) results across 3 different EEG datasets with >10x higher throughput than existing models, enabling the first model capable of long-range, continuous inference of variable-length EEG signals.

科目: 人工智能 (cs.AI); 人机交互 (cs.HC); 机器学习 (cs.LG)

Subjects: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)