随机配置网络(stochastic configuration network, SCN)是一种新兴的增量式神经网络模型, 与其他随机化神经网络方法不同, 它能够通过监督机制进行隐含层节点参数配置, 保证了模型的快速收敛性能. 因其具有学习效率高、人为干预程度低和泛化能力强等优点, 自2017年提出以来, SCN吸引了大量国内外学者的研究兴趣, 得到了快速的推广和发展. 从SCN的基础理论、典型算法变体、应用领域以及未来研究方向等方面切入, 全面地概述SCN研究进展. 首先, 从理论的角度分析SCN的算法原理、通用逼近性能及其优点; 其次, 重点研究深度SCN、二维SCN、鲁棒SCN、集成SCN、分布式并行SCN、正则化SCN等典型变体; 随后介绍SCN在硬件实现、计算机视觉、医学数据分析、故障检测与诊断、系统建模预测等不同领域的应用进展; 最后指出SCN在卷积神经网络架构、半监督学习、无监督学习、多视图学习、模糊神经网络、循环神经网络等研究方向的发展潜力.

Stochastic configuration network (SCN), as an emerging incremental neural network model, is different from other randomized neural network methods. It can configure the parameters of hidden layer nodes through supervision mechanisms, thereby ensuring the fast convergence performance of SCN. Due to the advantages of high learning efficiency, low human intervention, and strong generalization ability, SCN has attracted a large number of national and international scholars and developed rapidly since it was proposed in 2017. In this study, SCN research is summarized from the aspects of basic theories, typical algorithm variants, application fields, and future research directions of SCN. Firstly, the algorithm principles, universal approximation capacity, and advantages of SCN are analyzed theoretically. Secondly, typical variants of SCN are studied, such as DeepSCN, 2DSCN, Robust SCN, Ensemble SCN, Distributed SCN, Parallel SCN, and Regularized SCN. Then, the applications of SCN in different fields, including hardware implementation, computer vision, medical data analysis, fault detection and diagnosis, and system modeling and prediction are introduced. Finally, the development potential of SCN in convolutional neural network architectures, semi-supervised learning, unsupervised learning, multi-view learning, fuzzy neural network, and recurrent neural network is pointed out.

国家自然科学基金(61976216,62276265,61672522)