A sticky Poisson Hidden Markov Model for solving the problem of over-segmentation and rapid state switching in cortical datasets
PLOS One · 01.07.2025 · 20 (7) · e0325979
DOI: 10.1371/journal.pone.0325979 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 01.07.2025. Verfasst von Tianshu Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurobiology & Behavior, Stony Brook University, Stony Brook, NY, United States. Hauptthemen laut MEDLINE: Markov Chains, Cerebral Cortex, Models, Neurological. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NINDS NIH HHS, National Institute of Neurological Disorders and Stroke.
Abstract (Originalsprache)
The application of hidden Markov models (HMMs) to neural data has uncovered hidden states and signatures of neural dynamics that are relevant for sensory and cognitive processes. However, training an HMM on cortical data requires a careful handling of model selection, since models with more numerous hidden states generally have a higher likelihood on new (unseen) data. A potentially related problem is the occurrence of very rapid state switching after decoding the data with an HMM. The first problem can lead to overfitting and over-segmentation of the data. The second problem is due to intermediate-to-low self-transition probabilities and is at odds with many reports that hidden states in cortex tend to last from hundred of milliseconds to seconds. Here, we show that we can alleviate both problems by regularizing a Poisson-HMM during training so as to enforce large self-transition probabilities. We call this algorithm the ‘sticky Poisson-HMM’ (sPHMM). The sPHMM successfully eliminates rapid state switching, outperforming an alternative strategy based on an HMM with a large prior on the self-transition probabilities. When used together with the Bayesian Information Criterion for model selection, the sPHMM also captures the ground truth in surrogate datasets built to resemble the statistical properties of the experimental data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Neurobiology & Behavior, Stony Brook University, Stony Brook, NY, United States.
- Graduate Program in Neuroscience, Stony Brook University, Stony Brook, NY, United States.
- Center for Neural Circuit Dynamics, Stony Brook University, Stony Brook, NY, United States.
ORCID-Profile: Giancarlo La Camera
Förderung
- NINDS NIH HHS
- National Institute of Neurological Disorders and Stroke
Zitieren
APA
Li, T., & Camera, G. (2025). A sticky Poisson Hidden Markov Model for solving the problem of over-segmentation and rapid state switching in cortical datasets. PLOS One, 20(7), e0325979. https://doi.org/10.1371/journal.pone.0325979
Vancouver
Li T, Camera G. A sticky Poisson Hidden Markov Model for solving the problem of over-segmentation and rapid state switching in cortical datasets. PLOS One. 2025;20(7):e0325979. doi:10.1371/journal.pone.0325979
BibTeX
@article{Li2025,
author = {Li, Tianshu and Camera, Giancarlo La},
title = {A sticky Poisson Hidden Markov Model for solving the problem of over-segmentation and rapid state switching in cortical datasets},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {7},
pages = {e0325979},
doi = {10.1371/journal.pone.0325979}
}
EUVIMED