http://repository.wit.ie/id/eprint/3174 2016-08-23T11:27:21Z info:eu-repo/semantics/descriptiveMetadata http://repository.wit.ie/3174/ Ghostbusters: A Parts-based NMF Algorithm de Fréin, Ruairí Telecommunications Software and Systems Group An exact nonnegative matrix decomposition algorithm is proposed. This is achieved by 1) Taking a nonlinear approximation of a sparse real-valued dataset at a given tolerance-to-error constraint, e; 2) Choosing an arbitrary lectic ordering on the rows or column entries; And, then 3) systematically applying a closure operator, so that all closures are selected. Assuming a nonnegative hierarchical closure structure (a Galois lattice) ensures the data has a unique ordered overcomplete dictionary representation. Parts-based constraints on these closures can then be used to specify and supervise the form of the solution. We illustrate that this approach outperforms NMF on two standard NMF datasets: it exhibits the properties described above; It is correct and exact. IET and IEEE 2013-07 Article PeerReviewed application/pdf en http://repository.wit.ie/3174/1/ghostbusters.pdf de Fréin, Ruairí (2013) Ghostbusters: A Parts-based NMF Algorithm. 24th IET Irish Signals and Systems Conference (ISSC 2013), 24. pp. 1-8. http://digital-library.theiet.org/docserver/fulltext/conference/2013/002/20130050.pdf?expires=1384211572&id=id&accname=guest&checksum=9B3F0C4E2F0476A10F5E50C9D99E6E2A 10.1049/ic.2013.0050 info:eu-repo/semantics/objectFile info:eu-repo/semantics/humanStartPage