Neuroscience research has made immense progress over the last decade, but our understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary brain region and automatically reading out the information encoded in its neural activity remains out of reach. In this work, we build towards a first foundation model for neural spiking data that can solve a diverse set of tasks across multiple brain areas. We introduce a novel self-supervised modeling approach for population activity in which the model alternates between masking out and reconstructing neural activity across different time steps, neurons, and brain regions. To evaluate our approach, we design unsupervised and supervised prediction tasks using the International Brain Laboratory repeated site dataset, which is comprised of Neuropixels recordings targeting the same brain locations across 48 animals and experimental sessions. The prediction tasks include single-neuron and region-level activity prediction, forward prediction, and behavior decoding. We demonstrate that our multi-task-masking (MtM) approach significantly improves the performance of current state-of-the-art population models and enables multi-task learning. We also show that by training on multiple animals, we can improve the generalization ability of the model to unseen animals, paving the way for a foundation model of the brain at single-cell, single-spike resolution.

翻译：神经科学研究在过去十年取得了巨大进展，但我们对于大脑的理解仍然零散且不成体系：探测任意大脑区域并自动解读其神经活动所编码信息的梦想依然遥不可及。本研究致力于构建首个适用于神经尖峰数据的基础模型，该模型能够解决跨多个脑区的多样化任务。我们提出了一种新颖的群体活动自监督建模方法，该模型通过在不同时间步、神经元和脑区之间交替掩蔽与重建神经活动来实现。为评估该方法，我们利用国际脑实验室重复位点数据集设计了无监督与有监督的预测任务，该数据集包含针对48只动物和实验会话中相同脑区位置的Neuropixels记录。预测任务涵盖单神经元与区域层级活动预测、前向预测及行为解码。我们证明，所提出的多任务掩蔽（MtM）方法显著提升了当前最先进群体模型的性能，并实现了多任务学习。我们还发现，通过对多只动物进行训练，模型对未见动物的泛化能力得到提升，这为构建单细胞、单尖峰分辨率的大脑基础模型开辟了道路。