Unsupervised embedding of trajectories captures the latent structure of mobility.
Dakota S. MurrayJisung YoonSadamori KojakuRodrigo CostasWoo-Sung JungStasa MilojevicYong-Yeol AhnPublished in: CoRR (2020)
Keyphrases
- latent structure
- multidimensional scaling
- topic modeling
- discriminative learning
- low dimensional
- cluster analysis
- topic models
- latent variables
- euclidean distance
- negative matrix factorization
- vector space
- unsupervised learning
- generative model
- dimensionality reduction
- weakly supervised
- supervised learning
- group activities
- unsupervised manner
- maximum margin
- latent variable models
- high dimensional
- text mining
- kernel pca
- latent semantic indexing
- maximum likelihood
- data points