Can I read Two Recurrent Neural Networks With Reduced Model Complexity for Constrained l 1-Norm Optimization on EtoBox?

Two Recurrent Neural Networks With Reduced Model Complexity for Constrained l 1-Norm Optimization by Youshen Xia; Jun Wang; Zhenyu Lu; Liqing Huang is a Computer Science article available to read on EtoBox.

What is Two Recurrent Neural Networks With Reduced Model Complexity for Constrained l 1-Norm Optimization about?

Because of the robustness and sparsity performance of least absolute deviation (LAD or l 1 ) optimization, developing effective solution methods becomes an important topic. Recurrent neural networks (RNNs) are reported to be capable of effectively solving constrained l 1 -norm optimization problems, but their convergence speed is limited. To accelerate the convergence, this article introduces two RNNs, in form of continuous-and discrete-time systems, for solving l 1 -norm optimization problems with linear equality and inequality constraints. The RNNs are theoretically proven to be globally convergent to optimal solutions without any condition. With reduced model complexity, the two RNNs can significantly expedite constrained l 1 -norm optimization. Numerical simulation results show that the two RNNs spend much less computational time than related RNNs and numerical optimization algorithms for linearly constrained l 1 -norm optimization.

Who reads Two Recurrent Neural Networks With Reduced Model Complexity for Constrained l 1-Norm Optimization?

Author

Youshen Xia; Jun Wang; Zhenyu Lu; Liqing Huang

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)