pipette
ENEnglish

Linear NeuroPaint: An Efficient Baseline for Cross-Session Neural Alignment and Inpainting

Y. J. Yao, J. Xia, L. Paninski, K. D. Miller

Preprint

En palabras de los autores

Large-scale Neuropixels recordings sample many brain areas, but no single experimental session records every area of interest. NeuroPaint, a transformer-based autoencoder, integrates such recordings by aligning area-specific latent dynamics across sessions and "inpainting" activity in unrecorded areas. Could a linear model, which would be computationally efficient and potentially more interpretable, suffice to achieve this? To address this question, we introduce Linear NeuroPaint, a linear variant of NeuroPaint, and evaluate it on two multi-area Neuropixels datasets. Linear NeuroPaint achieves strong predictive performance on recorded areas, however, it is less accurate than nonlinear models at cross-area inpainting, despite extensive hyperparameter optimization. Moreover, its parameters are not readily interpretable: incomplete cross-session alignment leads parameter-defined neuron clusters to exhibit heterogeneous response profiles. Together, these results show that linear transformations are insufficient for cross-session alignment and cross-area prediction. Nevertheless, Linear NeuroPaint provides a computationally efficient baseline for benchmarking multi-session neural models.

Resultado principalLimitación que admiten los autores

Apareció: lunes, 12 de octubre. bioRxiv. Preprint, todavía sin revisión por pares.

DOI: 10.64898/2026.10.03.756082