Parallel Implementation of the Nonlinear Semi-NMF Based Alternating Optimization Method for Deep Neural Networks
Sign Up to like & getrecommendations! Published in 2017 at "Neural Processing Letters"
DOI: 10.1007/s11063-017-9642-2
Abstract: For computing weights of deep neural networks (DNNs), the backpropagation (BP) method has been widely used as a de-facto standard algorithm. Since the BP method is based on a stochastic gradient descent method using derivatives… read more here.
Keywords: nmf based; parallel implementation; method; nonlinear semi ... See more keywords
A Survey of Community Detection in Complex Networks Using Nonnegative Matrix Factorization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Computational Social Systems"
DOI: 10.1109/tcss.2021.3114419
Abstract: Community detection is one of the popular research topics in the field of complex networks analysis. It aims to identify communities, represented as cohesive subgroups or clusters, where nodes in the same community link to… read more here.
Keywords: complex networks; community; nonnegative matrix; community detection ... See more keywords
Initialization for NMF-based audio source separation using priors on encoding vectors
Sign Up to like & getrecommendations! Published in 2019 at "China Communications"
DOI: 10.23919/jcc.2019.09.013
Abstract: Nonnegative matrix factorization (NMF) has shown good performances on blind audio source separation (BASS). While the NMF analysis is a non-convex optimization problem when both the basis and encoding matrices need to be estimated simultaneously,… read more here.
Keywords: audio source; nmf based; separation; source separation ... See more keywords