A collaborative neurodynamic optimizer (recurrent networks plus particle swarm) is proposed for nonnegative canonical polyadic decomposition, with a claimed almost-sure global convergence guarantee and experiments on collinear and real-world tensors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Nonnegative Tensor Decomposition Via Collaborative Neurodynamic Optimization
A collaborative neurodynamic optimizer (recurrent networks plus particle swarm) is proposed for nonnegative canonical polyadic decomposition, with a claimed almost-sure global convergence guarantee and experiments on collinear and real-world tensors.