Distributed learning for feedforward neural networks with random weights using an event-triggered communication scheme

详细信息    查看全文

• 作者：Wu Ai^a ; ^b ; ^{aiwu818@gmail.com}Author Vitae ; Weisheng Chen^c ; ^{wshchen@126.com}Author Vitae ; Jin Xie^a ; ^{Static_6417@163.com}Author Vitae
• 关键词：Distributed learning ; Neural networks with random weights ; Consensus ; Distributed optimization ; Event-triggered communication
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：8 February 2017
• 年：2017
• 卷：224
• 期：Complete
• 页码：184-194
• 全文大小：1255 K
• 卷排序：224

文摘

This paper aims to develop distributed learning algorithms for feedforward neural networks with random weights (FNNRWs) by using event-triggered communication schemes. Based on this scheme, the communication process of each agent is driven by a trigger condition where the agents exchange information in an asynchronous manner, only when it is crucially required. To this end, the centralized FNNRW problem is cast as a set of distributed subproblems with consensus constrains imposed on the desired parameters and solved following the discrete-time zero-gradient-sum (ZGS) strategy. An event-triggered communication scheme is introduced to the ZGS-based FNNRW algorithm in order to avoid unnecessary transmission costs. This is particularly useful for the case when communication resource is limited. It is proved that the proposed event-triggered approach is exponentially convergent if the design parameter is chosen properly under strongly connected and weight-balanced agent interactions. Two numerical simulation examples are provided to verify the effectiveness of the proposed algorithm.