Скачать презентацию Nonnegative Matrix Factorization via Rank-one Downdate Nonnegative Скачать презентацию Nonnegative Matrix Factorization via Rank-one Downdate Nonnegative

d22ce344ca5834277bc333ccbde1b917.ppt

  • Количество слайдов: 50

Nonnegative Matrix Factorization via Rank-one Downdate Nonnegative Matrix Factorization via Rank-one Downdate

Nonnegative Matrix Factorization Nonnegative Matrix Factorization

2 by 1965 560 by 2 -2. 19 -0. 02 20 by 28 -3. 2 by 1965 560 by 2 -2. 19 -0. 02 20 by 28 -3. 19 1. 02 2 by 1

Singular Value Decomposition (SVD) Singular Value Decomposition (SVD)

History History

History History

History History

History History

History (Algorithms) History (Algorithms)

History (Algorithms) History (Algorithms)

First observation First observation

Power method • Computes the leading singular vectors/value (or eigenvector/value) of a matrix 1 Power method • Computes the leading singular vectors/value (or eigenvector/value) of a matrix 1 2 while not converged 3 4 5 6 end

Example • Computes the leading singular vectors/value (or eigenvector/value) of a matrix 2 while Example • Computes the leading singular vectors/value (or eigenvector/value) of a matrix 2 while not converged 3 4 5 6 end

Naive approach to NMF using this observation 1 2 3 4 5 6 for Naive approach to NMF using this observation 1 2 3 4 5 6 for all end for set Without step 5, this will simply compute the SVD (Jordan's algorithm, Camille Jordan 1874. )

Second observation Second observation

Modified power iteration 1 2 while not converged 3 4 5 6 7 8 Modified power iteration 1 2 while not converged 3 4 5 6 7 8 end

Modified power iteration: Demo A= Rank-1 submatrix Modified power iteration: Demo A= Rank-1 submatrix

Modified power iteration: Demo v: 0. 14 0. 07 0. 64 0. 41 0. Modified power iteration: Demo v: 0. 14 0. 07 0. 64 0. 41 0. 55 Rank-1 submatrix

Modified power iteration: Demo v: 0. 0 0. 64 0. 41 0. 55 Rank-1 Modified power iteration: Demo v: 0. 0 0. 64 0. 41 0. 55 Rank-1 submatrix

Modified power iteration: Demo v: 0. 0 0. 64 0. 41 0. 55 Rank-1 Modified power iteration: Demo v: 0. 0 0. 64 0. 41 0. 55 Rank-1 submatrix

Modified power iteration: Demo v: u: 0. 16 0. 21 0. 22 0. 44 Modified power iteration: Demo v: u: 0. 16 0. 21 0. 22 0. 44 0. 74 0. 20 0. 64 0. 41 0. 55 Rank-1 submatrix

Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 0. 64 0. 41 0. 55 Rank-1 submatrix

Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 0. 64 0. 41 0. 55 Rank-1 submatrix

Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 0. 60 0. 28 0. 59 Rank-1 submatrix

Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 0. 60 0. 28 0. 59 Rank-1 submatrix

Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 Modified power iteration: Demo v: u: 0. 0 0. 44 0. 74 0. 20 0. 60 0. 28 0. 59 Rank-1 submatrix Rank-1 Zero-out! submatrix

Modified power iteration: Demo Anew = Rank-1 submatrix Modified power iteration: Demo Anew = Rank-1 submatrix

Rank-one Downdata (R 1 D) 1 2 3 4 5 end for Rank-one Downdata (R 1 D) 1 2 3 4 5 end for

Objective function Objective function

Approx. Rank. One. Submatrix(A) Approx. Rank. One. Submatrix(A)

Rank-one Downdata (R 1 D) Rank-one Downdata (R 1 D)

Rank-one Downdata (R 1 D) Rank-one Downdata (R 1 D)

A simple model for text A simple model for text

Generating a corpus in the model Generating a corpus in the model

Theorem about text Theorem about text

LSI LSI

R 1 D R 1 D

Experimental results • Information retrieval task – TDT corpus (pilot study, v. 1. 3, Experimental results • Information retrieval task – TDT corpus (pilot study, v. 1. 3, 1997): news articles Identified topics (first few columns of ): Topic: president, clinton, house, white Topic: bosnian, serbs, bosnia, serb, nato, sarajevo, air, bihac Topic: haiti, military, aristide, haitian, troops, port, invasion, … Topic: simpson, defense, judge, case, jury, trial, angeles, los, court, … Topic: bill, today, senate, republicans, house, congress, republican, …

Experimental results • For topic: “OJ Simpson trial” (simpson, defense, judge, case, jury, trial) Experimental results • For topic: “OJ Simpson trial” (simpson, defense, judge, case, jury, trial) Document 1 Document 2 Document 3 Document 4 Allen Simpson Judge Gloves Kaelin Judge Defense Case Police Defence Statements Prosecution Defense Marcus Opening Defense Chicago Court Jury Roger Testimony Witness Legal Put Night Testify Yesterday Fit Knapsack Nicole Prosecution Today Cnn gloves Marc Problems Blood los jury Witness

Theorem about images Theorem about images

Experimental results Experimental results

LSI LSI

NMF-DIV NMF-DIV

R 1 D R 1 D

LSI LSI

NMF_DIV NMF_DIV

NMF_SC NMF_SC

R 1 D R 1 D