Random vector functional link network: recent developments, applications, and future directions

TL;DR

This paper reviews the development, variations, applications, and future prospects of the Random Vector Functional Link (RVFL) neural network, highlighting its advantages over traditional training methods and summarizing recent research advancements.

Contribution

It provides the first comprehensive review of RVFL models, covering shallow, ensemble, deep, and ensemble deep variants, along with hyperparameter optimization techniques and future research directions.

Findings

RVFL models offer fast training and universal approximation.

Variations include shallow, ensemble, deep, and ensemble deep RVFLs.

Future research can further improve RVFL architecture and learning algorithms.

Abstract

Neural networks have been successfully employed in various domains such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train the neural networks, however, it results in the issues of local minima, sensitivity to learning rate and slow convergence. To overcome these issues, randomization based neural networks such as random vector functional link (RVFL) network have been proposed. RVFL model has several characteristics such as fast training speed, direct links, simple architecture, and universal approximation capability, that make it a viable randomized neural network. This article presents the first comprehensive review of the evolution of RVFL model, which can serve as the extensive summary for the beginners as well as practitioners. We discuss the shallow RVFLs, ensemble RVFLs, deep RVFLs and ensemble deep RVFL models. The variations, improvements and applications of RVFL models are discussed in detail. Moreover, we discuss the different hyperparameter optimization techniques followed in the literature to improve the generalization performance of the RVFL model. Finally, we give potential future research directions/opportunities that can inspire the researchers to improve the RVFL's architecture and learning algorithm further.