l0-norm Based Centers Selection for Training Fault Tolerant RBF Networks and Selecting Centers

TL;DR

This paper introduces two novel ADMM-based algorithms for fault-tolerant RBF neural network training that simultaneously select centers, demonstrating superior performance under concurrent faults compared to existing methods.

Contribution

The paper proposes two new algorithms using MCP and l0-norm with hard threshold for center selection and fault tolerance in RBF networks, with proven convergence.

Findings

Algorithms outperform existing methods under concurrent faults.

Both methods guarantee global convergence under mild conditions.

Simulation results validate the effectiveness of the proposed approaches.

Abstract

The aim of this paper is to train an RBF neural network and select centers under concurrent faults. It is well known that fault tolerance is a very attractive property for neural networks. And center selection is an important procedure during the training process of an RBF neural network. In this paper, we devise two novel algorithms to address these two issues simultaneously. Both of them are based on the ADMM framework. In the first method, the minimax concave penalty (MCP) function is introduced to select centers. In the second method, an l0-norm term is directly used, and the hard threshold (HT) is utilized to address the l0-norm term. Under several mild conditions, we can prove that both methods can globally converge to a unique limit point. Simulation results show that, under concurrent fault, the proposed algorithms are superior to many existing methods.