Extreme learning machine: a new learning scheme of feedforward neural networks

By G. Huang, Qin-Yu Zhu, Chee Kheong Siew. 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), 2004

4,185 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/2b9c0e4d1d473aadbe1c2a76f75bc02bfa6416b0

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

1. G. Huang
2. Shiji Song
3. Gao Huang
4. Yuan Lan
5. Hongming Zhou
6. Dianhui Wang
7. Xiaojian Ding
8. Lei Chen

In Electrical and Electronic Engineering

1. G. Huang
2. Hongming Zhou
3. Xiaojian Ding
4. Lei Chen
5. Yuan Lan
6. Shiji Song
7. Dianhui Wang
8. Gao Huang

Citations in the corpus

• Performance Comparison of Support Vector Machine, Random Forest, and Extreme Learning Machine for Intrusion Detection (2018, background): “ELM is another name for single or multiple hidden layer feedforward neural networks [13].”
• Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition (2019, background): “[224] A. Addeh, A. Khormali, and N. A. Golilarz, ‘‘Control chart pattern recognition using RBF neural network with new training algorithm and practical features,’’ ISA Trans., vol. 79, pp. 202–216, Aug. 2018.”
• Determination of Amino Acid Nitrogen in Soy Sauce Using Near Infrared Spectroscopy Combined with Characteristic Variables Selection and Extreme Learning Machine (2013, methodology): “The Theory of ELM ELM, as a new fast learning algorithm, proposed by Huang et al. (2004, 2006), which has been developed for single hidden layer feedforward networks (SLFN).”
• Trends in extreme learning machines: A review (2015, background): “…aim of ELM is to simultaneously satisfy several salient targets (Huang, Ding, & Zhou, 2010; Huang, Zhou, et al., 2012; Huang, Zhu, et al., 2006; Huang et al., 2004): (1) Generalization performance: Most algorithms proposed for feedforward neural networks do not consider the generalization…”
• Spatial anomaly detection in sensor networks using neighborhood information (2017, methodology): “This extreme learning machine (ELM) approach was demonstrated by Huang et al. [67] , similar to random vector functional-link neural networks [68] , to perform on par with other machine learning methods, such as support vector machines, given enough hidden neurons.”
• A review on weight initialization strategies for neural networks (2021, methodology): “The input-to-hidden node weights in ELM were randomly initialized and output weights were obtained from Moore-Penrose inverse method (Huang et al. 2004).”
• A Semantic Approach to Host-Based Intrusion Detection Systems Using Contiguousand Discontiguous System Call Patterns (2014, background): “neural network, the extreme learning machine (ELM) [15], demonstrated superior performance against all data sets, and is discussed further in the body of the paper.”
• Minimum Variance Extreme Learning Machine for human action recognition (2014, background): “Extreme Learning Machine is a, relatively, new algorithm for Single-hidden Layer Feedforward Neural (SLFN) netorks training [1] that leads to fast network training requiring low human supervision.”
• A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks (2006, background): “OS-ELM originates from the batch learning extreme learning machine (ELM) [20]–[22], [27], [30] developed for SLFNs with additive and RBF nodes.”
• Learning the rules of a game: Neural conditioning in human-robot interaction with delayed rewards (2013, methodology): “In combination with tactile feedback reward / punishment facial expression speech gaze stimuli processing output learning network (operant conditioning) control system eye-cameras image processing ELM network (Hand shape recognition) marker environment player network's actions let's play rock paper ”
• Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows (2020, methodology): “San & Maulik (2018) utilized an extreme learning machine (Huang et al. 2004) based on MLP for developing an ROM of geophysical turbulence.”
• Regularized Extreme Learning Machine (2009, methodology): “ecently, Huang et al. proposed an “extreme learning machine (ELM)” [1][ 3 ], which is a Single Hidden Layer Feedforward Neural Network (SLFN) with the hidden neuron parameters [i.e., weights and bias for a multilayer perceptron (MLP) network, centers and width’s in a radial basis function(RBF) netwo”
• Rethinking and Improving the Robustness of Image Style Transfer (2021, background): “Our work is partly motivated by some theoretical and practical studies on random weights [17, 18, 29, 28, 40, 39, 5].”
• Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques (2019, methodology): “To increase the computational speed, an ELM was developed by Huang et al .”