Deep Recurrent Stochastic Configuration Networks for Modelling Nonlinear Dynamic Systems

TL;DR

This paper introduces DeepRSCN, a deep reservoir computing framework that efficiently models nonlinear dynamic systems with improved accuracy and generalization, using incremental construction and online learning algorithms.

Contribution

It proposes a novel deep recurrent stochastic configuration network architecture with incremental construction, supervisory parameter assignment, and online output weight updates for nonlinear system modeling.

Findings

DeepRSCN outperforms single-layer networks in efficiency and accuracy.

The framework effectively models complex nonlinear systems.

Experimental results validate superior generalization performance.

Abstract

Deep learning techniques have shown promise in many domain applications. This paper proposes a novel deep reservoir computing framework, termed deep recurrent stochastic configuration network (DeepRSCN) for modelling nonlinear dynamic systems. DeepRSCNs are incrementally constructed, with all reservoir nodes directly linked to the final output. The random parameters are assigned in the light of a supervisory mechanism, ensuring the universal approximation property of the built model. The output weights are updated online using the projection algorithm to handle the unknown dynamics. Given a set of training samples, DeepRSCNs can quickly generate learning representations, which consist of random basis functions with cascaded input and readout weights. Experimental results over a time series prediction, a nonlinear system identification problem, and two industrial data predictive analyses demonstrate that the proposed DeepRSCN outperforms the single-layer network in terms of modelling efficiency, learning capability, and generalization performance.