Foundation model of neural activity predicts response to new stimulus types

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 models<sup>1</sup> 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 dataset<sup>2</sup>. 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.

Authors

Institutions

Publication Details

Journal
Nature
Published
2025-04-09
DOI
https://doi.org/10.1038/s41586-025-08829-y
Citations
50
Primary Topic
Neural dynamics and brain function
Type
article
Field-Weighted Citation Impact
68.69
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Foundation model of neural activity predicts response to new stimulus types

R. Clay Reid, Dat Tran, Katrin Franke, Stelios Papadopoulos et al.
50 citations
Nature
Neural dynamics and brain function
68.69
article

Foundation model of neural activity predicts response to new stimulus types

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

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 models<sup>1</sup> 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 dataset<sup>2</sup>. 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.

NatureVol. 640(8058)
Allen Institute for Brain Science (US), Baylor College of Medicine (US), Neurosciences Institute (US), Max Planck Institute for Dynamics and Self-Organization (DE), Stanford Medicine (US), Allen Institute (US), University of Göttingen (DE), Rice University (US), University of Tübingen (DE), Stanford University (US)
Openalex Percentile: Top 0%
Neural dynamics and brain function
68.69
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.