ScholarGate
Asistents

Salīdzināt metodes

Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.

Neatūru matricas faktorizācija (NMF)×Word2Vec×
NozareMašīnmācīšanāsTeksta ieguve
SaimeLatent structureProcess / pipeline
Izcelsmes gads19992013
AutorsLee, D. D. & Seung, H. S.Tomas Mikolov et al.
TipsMatrix decomposition with non-negativity constraintsNeural word-embedding model
PirmavotsLee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791. DOI ↗Mikolov, T., Chen, K., Corrado, G. & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. link ↗
Citi nosaukumiNMF, NNMF, nonnegative matrix factorization, non-negative matrix approximationword embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri
Saistītās44
KopsavilkumsNon-negative Matrix Factorization (NMF) is a family of algorithms, introduced by Lee and Seung in their landmark 1999 Nature paper, that decomposes a non-negative data matrix V into the product of two lower-rank non-negative matrices W (basis components) and H (encoding coefficients). Unlike PCA or SVD, the non-negativity constraint forces the algorithm to learn strictly additive, parts-based representations, making the factors directly interpretable as building blocks of the original data.Word2Vec is a neural word-embedding technique introduced by Mikolov and colleagues in 2013 that maps each word in a text corpus to a dense numeric vector. Words that appear in similar contexts end up close together in the vector space, so the embeddings capture semantic similarity that can be measured arithmetically.
ScholarGateDatu kopa
  1. v1
  2. 3 Avoti
  3. PUBLISHED
  1. v1
  2. 1 Avoti
  3. PUBLISHED

Doties uz meklēšanu Lejupielādēt slaidus

ScholarGateSalīdzināt metodes: Non-negative Matrix Factorization · Word2Vec. Izgūts 2026-06-19 no https://scholargate.app/lv/compare