Revealing the core dimensions underlying representations in brains, behavior and AI
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_ | 1866914604681003008 |
|---|---|
| author | Mahner, Florian P. Lam, Ka Chun Pereira, Francisco Hebart, Martin N. |
| author_facet | Mahner, Florian P. Lam, Ka Chun Pereira, Francisco Hebart, Martin N. |
| contents | The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are often studied and compared through similarities between stimuli, current methods provide only limited access to the dimensions that shape these representations and are often limited in interpretability. To overcome these challenges, here we introduce Similarity-Based Representation Factorization (SRF), a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices derived from measured data. Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data, even for very sparsely sampled, incomplete data. The dimensions derived from these datasets match those obtained by task-specific models, predict independent behavioral properties, improve exploratory analysis, and offer higher power for confirmatory hypothesis testing than comparing similarity matrices. Together, these results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and leveraging the dimensions underlying representations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26921 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Revealing the core dimensions underlying representations in brains, behavior and AI Mahner, Florian P. Lam, Ka Chun Pereira, Francisco Hebart, Martin N. Computer Vision and Pattern Recognition Neurons and Cognition The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are often studied and compared through similarities between stimuli, current methods provide only limited access to the dimensions that shape these representations and are often limited in interpretability. To overcome these challenges, here we introduce Similarity-Based Representation Factorization (SRF), a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices derived from measured data. Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data, even for very sparsely sampled, incomplete data. The dimensions derived from these datasets match those obtained by task-specific models, predict independent behavioral properties, improve exploratory analysis, and offer higher power for confirmatory hypothesis testing than comparing similarity matrices. Together, these results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and leveraging the dimensions underlying representations. |
| title | Revealing the core dimensions underlying representations in brains, behavior and AI |
| topic | Computer Vision and Pattern Recognition Neurons and Cognition |
| url | https://arxiv.org/abs/2605.26921 |