Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908886387130368 |
|---|---|
| author | Bishop, William E. Hesselink, Luuk W. Englitz, Bernhard Ahrens, Misha B. Fitzgerald, James E. |
| author_facet | Bishop, William E. Hesselink, Luuk W. Englitz, Bernhard Ahrens, Misha B. Fitzgerald, James E. |
| contents | Many disciplines need quantitative models that synthesize experimental data across multiple instances of the same general system. For example, neuroscientists must combine data from the brains of many individual animals to understand the species' brain in general. However, typical machine learning models treat one system instance at a time. Here we introduce a machine learning framework, deep probabilistic model synthesis (DPMS), that leverages system properties auxiliary to the model to combine data across system instances. DPMS specifically uses variational inference to learn a conditional prior distribution and instance-specific posterior distributions over model parameters that respectively tie together the system instances and capture their unique structure. DPMS can synthesize a wide variety of model classes, such as those for regression, classification, and dimensionality reduction, and we demonstrate its ability to improve upon single-instance models on synthetic data and whole-brain neural activity data from larval zebrafish. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14161 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects Bishop, William E. Hesselink, Luuk W. Englitz, Bernhard Ahrens, Misha B. Fitzgerald, James E. Machine Learning Neurons and Cognition Many disciplines need quantitative models that synthesize experimental data across multiple instances of the same general system. For example, neuroscientists must combine data from the brains of many individual animals to understand the species' brain in general. However, typical machine learning models treat one system instance at a time. Here we introduce a machine learning framework, deep probabilistic model synthesis (DPMS), that leverages system properties auxiliary to the model to combine data across system instances. DPMS specifically uses variational inference to learn a conditional prior distribution and instance-specific posterior distributions over model parameters that respectively tie together the system instances and capture their unique structure. DPMS can synthesize a wide variety of model classes, such as those for regression, classification, and dimensionality reduction, and we demonstrate its ability to improve upon single-instance models on synthetic data and whole-brain neural activity data from larval zebrafish. |
| title | Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects |
| topic | Machine Learning Neurons and Cognition |
| url | https://arxiv.org/abs/2603.14161 |