A-SOiD, an active-learning platform for expert-guided, data-efficient discovery of behavior
- 21 February 2024
- journal article
- research article
- Published by Springer Nature in Nature Methods
- Vol. 21 (4) , 703-711
Abstract
To identify and extract naturalistic behavior, two methods have become popular: supervised and unsupervised. Each approach carries its own strengths and weaknesses (for example, user bias, training cost, complexity and action discovery), which the user must consider in their decision. Here, an active-learning platform, A-SOiD, blends these strengths, and in doing so, overcomes several of their inherent drawbacks. A-SOiD iteratively learns user-defined groups with a fraction of the usual training data, while attaining expansive classification through directed unsupervised classification. In socially interacting mice, A-SOiD outperformed standard methods despite requiring 85% less training data. Additionally, it isolated ethologically distinct mouse interactions via unsupervised classification. We observed similar performance and efficiency using nonhuman primate and human three-dimensional pose data. In both cases, the transparency in A-SOiD’s cluster definitions revealed the defining features of the supervised classification through a game-theoretic approach. To facilitate use, A-SOiD comes as an intuitive, open-source interface for efficient segmentation of user-defined behaviors and discovered sub-actions.Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- Hierarchical action encoding in prefrontal cortex of freely moving macaquesCell Reports, 2023
- Widespread coding of navigational variables in prefrontal cortexCurrent Biology, 2023
- Toward the explainability, transparency, and universality of machine learning for behavioral classification in neuroscienceCurrent Opinion in Neurobiology, 2022
- Anipose: A toolkit for robust markerless 3D pose estimationCell Reports, 2021
- Deep learning tools for the measurement of animal behavior in neuroscienceCurrent Opinion in Neurobiology, 2020
- An alternative SMOTE oversampling strategy for high-dimensional datasetsApplied Soft Computing, 2019
- Mass Cytometry of the Human Mucosal Immune System Identifies Tissue- and Disease-Associated Immune SubsetsImmunity, 2016
- Mapping Sub-Second Structure in Mouse BehaviorNeuron, 2015
- Density-Based Clustering Based on Hierarchical Density Estimates2013
- Mouse Social Recognition and PreferenceCurrent Protocols in Neuroscience, 2003