发表机构
Zyphra（Zyphra）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究推出3.8亿参数的EEG基础模型ZUNA1.1，其灵活性远超原模型ZUNA1，在EEG去噪与重建任务中性能达标且显著优于MNE包的球形样条插值，已以Apache 2.0许可开源发布。
AI 中文摘要
我们推出ZUNA1.1，这是一个具有3.8亿参数的扩散自编码器，用于灵活的脑电图（EEG）信号重建。ZUNA1.1能够重建最长达30秒的可变长度序列，支持任意头皮位置的任意数量EEG通道，除了重建完整通道外，还可重建通道内的任意时间区间。我们证明ZUNA1.1的性能至少与早期的ZUNA1模型相当，同时灵活性大幅提升，可处理广泛的重建任务。ZUNA1.1在脑电图去噪和重建任务中仍显著优于标准方法，如MNE包中普遍使用的球形样条插值。ZUNA1.1模型以宽松的Apache 2.0许可开源发布。
英文摘要
We introduce ZUNA1.1, a 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction. ZUNA1.1 is capable of reconstructing variable length sequences of up to 30s, with an arbitrary number of EEG channels at arbitrary scalp locations, and can reconstruct arbitrary temporal intervals within channels in addition to reconstructing entire channels. We demonstrate that ZUNA1.1 performs at least on par with our earlier ZUNA1 model, while being far more flexible and capable of handling a wide range of reconstruction tasks. ZUNA1.1 continues to substantially outperform standard EEG denoising and reconstruction methods such as spherical spline interpolation, which is ubiquitously deployed in the MNE package. The ZUNA1.1 model is released open source under the permissive Apache 2.0 license.
