A Compact Constraint Incremental Method for Random Weight Networks and Its Application
- 10 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (11) , 16936-16944
Abstract
Incremental random weight networks (IRWNs) face the issues of weak generalization and complicated network structure. There is an important reason: the learning parameters of IRWNs are determined in a random fashion without guidance, which may increase many redundant hidden nodes, and thereby leading to inferior performance. To resolve this issue, a novel IRWN with compact constraint that guides the assignment of random learning parameters (CCIRWN) is developed in this brief. Using the iteration method of Greville, a compact constraint that simultaneously assures the quality of generated hidden nodes and the convergence of the CCIRWN is built to perform learning parameter configuration. Meanwhile, the output weights of the CCIRWN are assessed analytically. Two types of learning methods for constructing the CCIRWN are proposed. Finally, the performance evaluation of the proposed CCIRWN is undertaken on the 1-D nonlinear function approximation, several real-world datasets, and data-driven estimation based on the industrial data. Numerical and industrial examples indicate that the proposed CCIRWN with compact structure can achieve favorable generalization ability.Keywords
Funding Information
- National Natural Science Foundation of China (62003293, 61973306, 32102075)
- Qinglan Project of Jiangsu Province; and
- Nature Science Foundation of Jiangsu Province (BK20191043, BK20200086)
This publication has 30 references indexed in Scilit:
- A further study on the inequality constraints in stochastic configuration networksInformation Sciences, 2019
- Deep Attributed Network Embedding by Preserving Structure and Attribute InformationIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019
- A survey on metaheuristic optimization for random single-hidden layer feedforward neural networkNeurocomputing, 2019
- Modeling and control of mine main fan switchover systemISA Transactions, 2019
- Ristretto: A Framework for Empirical Study of Resource-Efficient Inference in Convolutional Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2018
- A Novel Pruning Algorithm for Smoothing Feedforward Neural Networks Based on Group Lasso MethodIEEE Transactions on Neural Networks and Learning Systems, 2017
- Deep Convolutional Neural Network for Inverse Problems in ImagingIEEE Transactions on Image Processing, 2017
- Stochastic Configuration Networks: Fundamentals and AlgorithmsIEEE Transactions on Cybernetics, 2017
- Insights into randomized algorithms for neural networks: Practical issues and common pitfallsInformation Sciences, 2017
- Neural network load forecasting with weather ensemble predictionsIEEE Transactions on Power Systems, 2002