May 14, 2024, 4:43 a.m. | Ida Egendal, Rasmus Froberg Br{\o}ndum, Marta Pelizzola, Asger Hobolth, Martin B{\o}gsted

cs.LG updates on arXiv.org arxiv.org

arXiv:2405.07879v1 Announce Type: cross
Abstract: The aim of this study is to provide a foundation to understand the relationship between non-negative matrix factorization (NMF) and non-negative autoencoders enabling proper interpretation and understanding of autoencoder-based alternatives to NMF. Since its introduction, NMF has been a popular tool for extracting interpretable, low-dimensional representations of high-dimensional data. However, recently, several studies have proposed to replace NMF with autoencoders. This increasing popularity of autoencoders warrants an investigation on whether this replacement is in general …

abstract aim application arxiv autoencoder autoencoders cs.lg enabling extraction factorization foundation interpretation introduction matrix negative relationship stat.ap study type understanding

Senior Machine Learning Engineer

@ GPTZero | Toronto, Canada

Software Engineer III -Full Stack Developer - ModelOps, MLOps

@ JPMorgan Chase & Co. | NY, United States

Senior Lead Software Engineer - Full Stack Senior Developer - ModelOps, MLOps

@ JPMorgan Chase & Co. | NY, United States

Software Engineer III - Full Stack Developer - ModelOps, MLOps

@ JPMorgan Chase & Co. | NY, United States

Research Scientist (m/w/d) - Numerische Simulation Laser-Materie-Wechselwirkung

@ Fraunhofer-Gesellschaft | Freiburg, DE, 79104

Research Scientist, Speech Real-Time Dialog

@ Google | Mountain View, CA, USA