GPT2MEG：对MEG进行量化以实现自回归生成
GPT2MEG: Quantizing MEG for Autoregressive Generation
AI总结：
GPT2MEG通过自回归训练和量化技术，实现了对MEG数据的高精度生成与模拟，优于现有方法。
摘要：
基于自监督目标训练的基础模型越来越多地应用于脑电记录，但对真实多通道神经时间序列进行自回归生成仍相对研究较少，特别是对于磁脑图（MEG）。我们研究了（i）修改后的多通道WaveNet变体和（ii）一种GPT-2风格的Transformer，通过在未标记的MEG上进行下一步预测进行自回归训练。对于Transformer，我们提出了一种简单的量化/分词和嵌入方案（通道、受试者和任务条件嵌入），该方案重新利用语言模型架构来处理连续、高频率的多通道时间序列，并能够实现任务诱发活动的条件模拟。在预测、长周期生成和下游解码中，GPT2MEG比WaveNet变体和线性自回归基线更准确地再现了真实MEG的时序、频谱和任务诱发统计特性，并通过受试者嵌入扩展到多个受试者。代码可在https://github.com/ricsinaruto/MEG-transfer-decoding获取。
英文摘要：
Foundation models trained with self-supervised objectives are increasingly applied to brain recordings, but autoregressive generation of realistic multichannel neural time series remains comparatively underexplored, particularly for Magnetoencephalography (MEG). We study (i) modified multichannel WaveNet variants and (ii) a GPT-2-style Transformer, autoregressively trained by next-step prediction on unlabelled MEG. For the Transformer, we propose a simple quantization/tokenization and embedding scheme (channel, subject, and task-condition embeddings) that repurposes a language-model architecture for continuous, high-rate multichannel time series and enables conditional simulation of task-evoked activity. Across forecasting, long-horizon generation, and downstream decoding, GPT2MEG more faithfully reproduces temporal, spectral, and task-evoked statistics of real MEG than WaveNet variants and linear autoregressive baselines, and scales to multiple subjects via subject embeddings. Code available at https://github.com/ricsinaruto/MEG-transfer-decoding.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
