Trends in extreme learning machines: A review

By Gao Huang, G. Huang, Shiji Song, Keyou You. Neural Networks, 2015

1,704 citations recorded by the source corpus.

Extreme learning machine (ELM) has gained increasing interest from various research fields recently. In this review, we aim to report the current state of the theoretical research and practical advances on this subject. We first give an overview of ELM from the theoretical perspective, including the interpolation theory, universal approximation capability, and generalization ability. Then we focus on the various improvements made to ELM which further improve its stability, sparsity and accuracy under general or specific conditions. Apart from classification and regression, ELM has recently been extended for clustering, feature selection, representational learning and many other learning tasks. These newly emerging algorithms greatly expand the applications of ELM. From implementation aspect, hardware implementation and parallel computation techniques have substantially sped up the training of ELM, making it feasible for big data processing and real-time reasoning. Due to its remarkable efficiency, simplicity, and impressive generalization performance, ELM have been applied in a variety of domains, such as biomedical engineering, computer vision, system identification, and control and robotics. In this review, we try to provide a comprehensive view of these advances in ELM together with its future perspectives.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/818e627defcd36477b6d39ec5fc4d02a479e7c37

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

A review of neural networks in plant disease detection using hyperspectral data (2018, background): “proposed to train single hidden-layer forward network [101,102], and this concept has been extended to multihidden-layer networks [103] and kernel learning [104].”
Market impact analysis via deep learned architectures (2018, methodology): “[5], which has been successfully used as a supervised learning model in many tasks [27].”
Local Receptive Fields Based Extreme Learning Machine (2015, background): “This section gives a brief review of ELM, CNN and HTM. Detailed reviews of ELM can be found in Huang et al. [13], [26].”
A Survey on ensemble learning under the era of deep learning (2021, methodology): “For the short-term load forecasting, Li et al. (Li et al. 2020) proposed an ensemble learning algorithm based on wavelet transform (Daubechies and Bates 1993), extreme learning machine (ELM) (Ding et al. 2015; Huang et al. 2015) and partial least squares regression (PLSR) (Geladi and Kowalski 1986).”
Nondestructive Detection of Postharvest Quality of Cherry Tomatoes Using a Portable NIR Spectrometer and Chemometric Algorithms (2019, methodology): “The number of hidden nodes was optimized by cross-validation, and in this study, the number of hidden nodes were optimized from 2 to 50 (Huang et al. 2015).”
Fusing audio, visual and textual clues for sentiment analysis from multimodal content (2016, background): “The best performance has been obtained with the extreme learning machine (ELM) [3] [4] [5], an emerging learning technique that provides efficient unified solutions to generalized feedforward networks including (but not limited to) single-/multihidden-layer neural networks, radial basis function…”