人脑中的柏拉图式表征：无监督恢复普适几何

摘要

强柏拉图表示假说认为，人工神经网络中的表示收敛可以被建设性地利用：即使没有配对数据，嵌入向量也能通过一个通用潜在空间在不同模型之间进行翻译。我们探究人类大脑中是否能恢复类似的几何结构。利用自然场景数据集中的fMRI数据，我们提出了一种自监督编码器，它仅通过重复刺激呈现从脑数据中学习受试者特定的嵌入。我们证明，这些独立学习的空间可以通过无监督正交旋转在不同受试者之间进行翻译，无需跨受试者配对样本或中间模型表示。将成对旋转同步到一个共享潜在空间中，进一步改善了跨受试者检索，这表明受试者特定空间与一个共同坐标系相互兼容。这些结果为人类视觉皮层中存在共享的神经几何结构提供了证据：受试者特定的fMRI表示在个体之间近似等距，并且可以通过纯几何变换进行翻译。

English

The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively: embeddings can be translated across models through a universal latent space without paired data. We ask whether an analogous geometry can be recovered across human brains. Using fMRI data from the Natural Scenes Dataset, we propose a self-supervised encoder that learns subject-specific embeddings from brain data alone by exploiting repeated stimulus presentations. We show that these independently learned spaces can be translated across subjects using unsupervised orthogonal rotations, without paired cross-subject samples or intermediate model representations. Synchronizing pairwise rotations into a single shared latent space further improves cross-subject retrieval, indicating that subject-specific spaces are mutually compatible with a common coordinate system. These results provide evidence for a shared neural geometry in the human visual cortex: subject-specific fMRI representations are approximately isometric across individuals and can be translated through purely geometric transformations.