Metraipolis › archive › dc_cf5578a02cd1
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity — arXiv:2111.02338
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2111.02338
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:32:07.131Z
- SHA-256 of the archived text
635fd93b684d23daf5e68b4b6344b5c3096a1f360cd28cf5c8e1906cf102a6ce- Stable URL of this page
https://metraipolis.com/documento/dc_cf5578a02cd1
How to cite
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity — arXiv:2111.02338 — arXiv (en), https://arxiv.org/abs/2111.02338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf5578a02cd1 (Metraipolis archive dc_cf5578a02cd1, sha256 635fd93b684d23daf5e68b4b6344b5c3096a1f360cd28cf5c8e1906cf102a6ce)
BibTeX
@misc{dccf5578a02cd1,
title = {Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity — arXiv:2111.02338},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2111.02338},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf5578a02cd1; sha256 635fd93b684d23daf5e68b4b6344b5c3096a1f360cd28cf5c8e1906cf102a6ce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2111.02338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Meaningful and simplified representations of neural activity can yield insights into how and what information is being processed within a neural circuit. However, without labels, finding representations that reveal the link between the brain and behavior can be challenging. Here, we introduce a novel unsupervised approach for learning disentangled representations of neural activity called Swap-VAE. Our approach combines a generative modeling framework with an instance-specific alignment loss that tries to maximize the representational similarity between transformed views of the input (brain state). These transformed (or augmented) views are created by dropping out neurons and jittering samples in time, which intuitively should lead the network to a representation that maintains both temporal consistency and invariance to the specific neurons used to represent the neural state. Through evaluations on both synthetic data and neural recordings from hundreds of neurons in different primate brains, we show that it is possible to build representations that disentangle neural datasets along relevant latent dimensions linked to behavior. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2111.02338 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T08:24:13.943Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).