Random Vector Functional Link Neural Network based Ensemble Deep Learning
This work addresses efficiency in deep learning for researchers and practitioners by offering a faster alternative to traditional ensembling methods, though it is incremental as it builds on existing RVFL networks.
The authors tackled the challenge of improving deep learning efficiency by proposing a deep Random Vector Functional Link (dRVFL) network with fixed random hidden layers and an ensemble version (edRVFL) that trains a single network for ensembling, achieving superior performance on benchmark datasets.
In this paper, we propose a deep learning framework based on randomized neural network. In particular, inspired by the principles of Random Vector Functional Link (RVFL) network, we present a deep RVFL network (dRVFL) with stacked layers. The parameters of the hidden layers of the dRVFL are randomly generated within a suitable range and kept fixed while the output weights are computed using the closed form solution as in a standard RVFL network. We also propose an ensemble deep network (edRVFL) that can be regarded as a marriage of ensemble learning with deep learning. Unlike traditional ensembling approaches that require training several models independently from scratch, edRVFL is obtained by training a single dRVFL network once. Both dRVFL and edRVFL frameworks are generic and can be used with any RVFL variant. To illustrate this, we integrate the deep learning networks with a recently proposed sparse-pretrained RVFL (SP-RVFL). Extensive experiments on benchmark datasets from diverse domains show the superior performance of our proposed deep RVFL networks.