Non-negative matrix factorization
Jump to navigation
Jump to search
General
- Original data must be non-negative
- for K latent variables << min(m,n)
- W is a tall matrix, H is the wide matrix
- For image analysis, W is the "basis images", like the topic centroid
- Label is based on the H matrix
- Works well with images since pixels are always non-negative
Compare vs PCA
- PCA can have negative values
- Items are in the rows
- Topics are linear combinations of words, documents are linear combinations of topics
- sparse ( non-smooth NMF)
Compare vs K-Means
- K means are bad at unbalanced problems
- K means implies K centroids mu_i where you minimize the cost function
- Class membership matrix, one hot encoded