Minimum-volume-regularized weighted symmetric nonnegative matrix factorization for clustering.
Tianxiang GaoSigurdur OlofssonSongtao LuPublished in: GlobalSIP (2016)
Keyphrases
- nonnegative matrix factorization
- nonnegative matrix
- least squares
- minimum volume
- spectral clustering
- negative matrix factorization
- matrix factorization
- sparsity constraints
- document clustering
- data representation
- objective function
- clustering algorithm
- principal component analysis
- xml documents
- unsupervised learning
- cluster analysis
- information retrieval
- original data
- novelty detection
- k means
- missing data
- optical flow
- data dependent
- pattern recognition