发现人脑视觉皮层存在共享几何结构，可无监督对齐不同个体脑数据。
Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
- 基于重复刺激的自监督编码器，仅用脑数据学习个体表征。
- 通过无监督正交旋转实现跨被试表征对齐，无需配对数据。
- 揭示人脑视觉皮层存在近似保距的通用坐标系，适合神经解码研究。
强柏拉图表征假说认为，人工神经网络中的表征收敛可被用于构建通用潜在空间，实现模型间嵌入的无监督转换。我们探讨该几何是否存在于人脑中。利用自然场景数据集的fMRI数据，提出一种自监督编码器，仅通过重复刺激呈现，从脑数据中学习个体特异性嵌入。结果显示，这些独立学习的空间可通过无监督正交旋转在被试间对齐，无需跨被试配对样本或中间模型表示。将成对旋转同步为单一共享潜在空间进一步提升跨被试检索效果，表明个体特异性空间在共同坐标系下具相互兼容性。结果支持人类视觉皮层存在共享神经几何：个体间fMRI表征近似等距，可通过纯几何变换相互转换。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。