Mixed Membership
Cross-source consensus on Mixed Membership from 1 sources and 4 claims.
1 sources · 4 claims
How it works
Comparisons
Highlighted claims
- Each subject's latent edge-strength vector is represented as a convex combination of shared templates. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis
- The mixture structure allows a subject to express several templates in different proportions rather than belong to one hard cluster. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis
- Subject weights lie on a simplex and sum to one across templates. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis
- BALM becomes more advantageous as memberships overlap, but is less advantaged when the truth is nearly categorical. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis