Extreme Learning Machine for Regression and Multiclass Classification

By G. Huang, Hongming Zhou, Xiaojian Ding, Rui Zhang. 2012

5,242 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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 Computer Vision and Pattern Recognition

Citations in the corpus

Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research (2015, background): “Furthermore, a version of the ELM that supports kernel functions (ELM-K) has recently been proposed (Huang et al., 2012).”
LSTM-Based EEG Classification in Motor Imagery Tasks (2018, methodology): “[27] proposed a comprehensive strategy combining WPD, CSP and kernel extreme learning machine (ELM) [28].”
Semi-Supervised and Unsupervised Extreme Learning Machines (2014, background): “This phenomenon is consistent with the empirical results given in the ELMs literature [23]; the ELM usually exhibits more evident advantage on data sets with higher number of classes.”
Deep Learning Advances in Computer Vision with 3D Data (2017, methodology): “The network consisted of several stacked Spectral-Spatial Feature Learning Units (SSFLUs) and a Kernel-based Extreme Learning Machine (KELM) [Huang et al. 2012] on top for performing the classiﬁcation.”
Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification (2015, methodology): “ELM [30], [31] is a neural network with only one hidden layer and one linear output layer.”
Probabilistic Forecasting of Wind Power Generation Using Extreme Learning Machine (2014, methodology): “ELM is simply a single hidden-layer feedforward neural network [19], [21], [22].”
An Extra Tree Regression Model for Discharge Coefficient Prediction: Novel, Practical Applications in the Hydraulic Sector and Future Research Directions (2021, methodology): “Since the classical machine learning algorithms suffer from latency due to the iterative approach they employ, ELM is proposed as an effective approach to overcome the latency problems [34, 35].”
Enhanced image classification with a fast-learning shallow convolutional neural network (2015, methodology): “The fast training method we use has been developed independently several times [6–9] and has gained increasing recognition in recent years—see [10–14] for recent reviews.”
Do we need hundreds of classifiers to solve real world classification problems? (2014, methodology): “40. elm m, extreme learning machine (Huang et al., 2012) implemented in Matlab using the code freely available9.”
The Role of AI, Machine Learning, and Big Data in Digital Twinning: A Systematic Literature Review, Challenges, and Opportunities (2021, methodology): “past DT-data is used to train a single hidden layer neural network for better prediction of gradual faults and detection of its causes, using extreme learning machine (ELM) [109].”
A systematic literature review on machine learning applications for sustainable agriculture supply chain performance (2020, methodology): “…aggregation (bagging), AdaBoost, stacked generalization (blending), and gradient boosted regression trees (GBRT) Regression Analysis A classical predictive model that expresses the relationship between inputs and an output parameter in the form of an equation (Nasrabadi, 2007; Huang et al. 2012).”
An extensive experimental survey of regression methods (2019, methodology): “kelm is the ELM neural network with Gaussian kernel [63] using the 1184 publicly available Matlab code(9).”