An Interpretable Constructive Algorithm for Incremental Random Weight Neural Networks and Its Application

by   Jing Nan, et al.
Northeastern University
China University of Mining and Technology

Incremental random weight neural networks (IRWNNs) have gained attention in view of its easy implementation and fast learning. However, a significant drawback of IRWNNs is that the elationship between the hidden parameters (node)and the residual error (model performance) is difficult to be interpreted. To address the above issue, this article proposes an interpretable constructive algorithm (ICA) with geometric information constraint. First, based on the geometric relationship between the hidden parameters and the residual error, an interpretable geometric information constraint is proposed to randomly assign the hidden parameters. Meanwhile, a node pool strategy is employed to obtain hidden parameters that is more conducive to convergence from hidden parameters satisfying the proposed constraint. Furthermore, the universal approximation property of the ICA is proved. Finally, a lightweight version of ICA is presented for large-scale data modeling tasks. Experimental results on six benchmark datasets and a numerical simulation dataset demonstrate that the ICA outperforms other constructive algorithms in terms of modeling speed, model accuracy, and model network structure. Besides, two practical industrial application case are used to validate the effectiveness of ICA in practical applications.


page 1

page 6


Stochastic Configuration Networks: Fundamentals and Algorithms

This paper contributes to a development of randomized methods for neural...

Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach

It is well known that Artificial Neural Networks are universal approxima...

A Method of Generating Random Weights and Biases in Feedforward Neural Networks with Random Hidden Nodes

Neural networks with random hidden nodes have gained increasing interest...

Orthogonal Stochastic Configuration Networks with Adaptive Construction Parameter for Data Analytics

As a randomized learner model, SCNs are remarkable that the random weigh...

A New Constructive Method to Optimize Neural Network Architecture and Generalization

In this paper, after analyzing the reasons of poor generalization and ov...

MVDLite: A Light-weight Representation of Model View Definition with Fast Validation for BIM Applications

Model View Definition (MVD) is the standard methodology to define the pa...

Please sign up or login with your details

Forgot password? Click here to reset