神经活动的基础模型预测对新刺激类型的反应，这一成果由美国贝勒医学院心Andreas S. Tolias课题组经过不懈努力而取得。该项研究成果发表在2025年4月9日出版的《自然》上。

在这里，小组从多个小鼠的视觉皮层收集了大量的神经活动，并训练了一个基础模型来准确预测神经元对任意自然视频的反应。该模型推广到训练最少的新小鼠，并成功预测了各种新刺激域（如相干运动和噪声模式）的反应。除了神经反应预测，该模型还准确预测了MICrONS功能连接组数据中的解剖细胞类型、树突特征和神经元连接。他们的工作是建立大脑基础模型的关键一步。随着神经科学积累更大的多模态数据集，基础模型将揭示统计规律，使其能够快速适应新任务并加速研究。

据介绍，神经回路的复杂性使得破译大脑的智能算法具有挑战性。最近在深度学习方面的突破已经产生了精确模拟大脑活动的模型，增强了他们对大脑计算目标和神经编码的理解。然而，这些模型很难泛化到它们的训练分布之外，限制了它们的实用性。在大量数据集上训练的基础模型的出现，引入了一种具有显著泛化能力的新人工智能范式。

附：英文原文

Title: Foundation model of neural activity predicts response to new stimulus types

Author: Wang, Eric Y., Fahey, Paul G., Ding, Zhuokun, Papadopoulos, Stelios, Ponder, Kayla, Weis, Marissa A., Chang, Andersen, Muhammad, Taliah, Patel, Saumil, Ding, Zhiwei, Tran, Dat, Fu, Jiakun, Schneider-Mizell, Casey M., Reid, R. Clay, Collman, Forrest, da Costa, Nuno Maarico, Franke, Katrin, Ecker, Alexander S., Reimer, Jacob, Pitkow, Xaq, Sinz, Fabian H., Tolias, Andreas S.

Issue&Volume: 2025-04-09

Abstract: The complexity of neural circuits makes it challenging to decipher the brain’s algorithms of intelligence. Recent breakthroughs in deep learning have produced models that accurately simulate brain activity, enhancing our understanding of the brain’s computational objectives and neural coding. However, it is difficult for such models to generalize beyond their training distribution, limiting their utility. The emergence of foundation models1 trained on vast datasets has introduced a new artificial intelligence paradigm with remarkable generalization capabilities. Here we collected large amounts of neural activity from visual cortices of multiple mice and trained a foundation model to accurately predict neuronal responses to arbitrary natural videos. This model generalized to new mice with minimal training and successfully predicted responses across various new stimulus domains, such as coherent motion and noise patterns. Beyond neural response prediction, the model also accurately predicted anatomical cell types, dendritic features and neuronal connectivity within the MICrONS functional connectomics dataset2. Our work is a crucial step towards building foundation models of the brain. As neuroscience accumulates larger, multimodal datasets, foundation models will reveal statistical regularities, enable rapid adaptation to new tasks and accelerate research.

DOI: 10.1038/s41586-025-08829-y

Source: https://www.nature.com/articles/s41586-025-08829-y