Letters: A new adaptive momentum algorithm for split-complex recurrent neural networks

Authors:
Dongpo Xu;Hongmei Shao;Huisheng Zhang
Affiliations:
College of Science, Harbin Engineering University, Harbin 150001, PR China;College of Science, China University of Petroleum, Qingdao 266555, PR China;Department of Mathematics, Dalian Maritime University, Dalian 116026, PR China
Venue:
Neurocomputing
Year:
2012

Citing 12
Cited 0

Matrix analysis

Matrix analysis
A Complex-Valued RTRL Algorithm for Recurrent Neural Networks

Neural Computation
Single-layered complex-valued neural network for real-valued classification problems

Neurocomputing
Complex Valued Nonlinear Adaptive Filters: Noncircularity, Widely Linear and Neural Models

Complex Valued Nonlinear Adaptive Filters: Noncircularity, Widely Linear and Neural Models
When does online BP training converge?

IEEE Transactions on Neural Networks
A modified gradient-based neuro-fuzzy learning algorithm and its convergence

Information Sciences: an International Journal
Convergence analysis of three classes of split-complex gradient algorithms for complex-valued recurrent neural networks

Neural Computation
Convergence analysis of online gradient method for BP neural networks

Neural Networks
Convergence analysis of a back-propagation algorithm with adaptive momentum

Neurocomputing
The complex backpropagation algorithm

IEEE Transactions on Signal Processing
Stability of steepest descent with momentum for quadratic functions

IEEE Transactions on Neural Networks
Convergence of gradient method with momentum for two-Layer feedforward neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

The momentum method is a commonly used method to accelerate the learning of neural networks. In this paper, a new adaptive momentum algorithm is proposed for split-complex recurrent neural networks training. Different from other momentum methods, this new algorithm uses a variable gain factor and a variable learning rate to speed up the convergence and smooth the weight trace. The global convergence of the new algorithm is proved under mild conditions. Numerical results show that the algorithm is efficient for the given test problems.