期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 34, 期 8, 页码 4881-4891出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3125457
关键词
Optimization; Neurodynamics; Sparse matrices; Matrix converters; Linear programming; Search problems; Recurrent neural networks; Mixed-integer optimization; sparse nonnegative matrix factorization (SNMF); two-timescale duplex neurodynamics
In this article, the sparse nonnegative matrix factorization problem is formulated as a mixed-integer bicriteria optimization problem. A two-timescale duplex neurodynamic approach is used to solve the problem, achieving low error, high sparsity, and high score.
In this article, sparse nonnegative matrix factorization (SNMF) is formulated as a mixed-integer bicriteria optimization problem for minimizing matrix factorization errors and maximizing factorized matrix sparsity based on an exact binary representation of $l_{0}$ matrix norm. The binary constraints of the problem are then equivalently replaced with bilinear constraints to convert the problem to a biconvex problem. The reformulated biconvex problem is finally solved by using a two-timescale duplex neurodynamic approach consisting of two recurrent neural networks (RNNs) operating collaboratively at two timescales. A Gaussian score (GS) is defined as to integrate the bicriteria of factorization errors and sparsity of resulting matrices. The performance of the proposed neurodynamic approach is substantiated in terms of low factorization errors, high sparsity, and high GS on four benchmark datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据