A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks

By Nan-Ying Liang, G. Huang, Paramasivan Saratchandran, Narasimhan Sundararajan. 2006

1,906 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, 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 Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “An initial work in this area is done by Liang et al. [32].”
Machine Learning and Integrative Analysis of Biomedical Big Data (2019, methodology): “OS-ELM based algorithms can learn data one sample at a time or as chunks of samples, and have been employed for nonlinear classification and regression applications.”
Incremental on-line learning: A review and comparison of state of the art algorithms (2018, methodology): “Related Work Numerous incremental and on-line algorithms have been published, often adapting existing batch methods to the incremental setting [7, 8].”
Online Learning: A Comprehensive Survey (2018, background): “…kernel-based online learning approaches, another rich family of nonlinear online learning algorithms follows the general idea of neural network based learning approaches (Williams and Zipser, 1989; Platt, 1991; Carpenter et al., 1991; LeCun et al., 1998; Liang et al., 2006; Polikar et al., 2001).”
Artificial Intelligence and COVID-19: Deep Learning Approaches for Diagnosis and Treatment (2020, background): “There are several other studies that have previously scrutinized ELM with fixed network architectures [30], [32]–[34].”
Power Utility Nontechnical Loss Analysis With Extreme Learning Machine Method (2008, methodology): “In order to handle online applications, the online variant of ELM referred to OS-ELM has been proposed in [27].”
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, background): “Online learning has been shown to be computationally more e ffi cient than traditional batch learners [288, 289].”
Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning (2009, background): “[5], [6], [9], [10] proved and demonstrated that iterative techniques are not required in adjusting parameters of SLFNs at all.”
Semi-Supervised and Unsupervised Extreme Learning Machines (2014, background): “for specific problems, such as ELMs for online sequential data [29]–[31], ELMs for noisy/missing data [32]–[34], ELMs for imbalanced data [35], and so on.”
Endowing a Content-Based Medical Image Retrieval System with Perceptual Similarity Using Ensemble Strategy (2016, methodology): “The main strengths of the ELM technique are (i) they have only one parameter to adjust, which is the hidden layer size L, and (ii) they are trained in a single step [35, 36].”
Compressed-Domain Ship Detection on Spaceborne Optical Image Using Deep Neural Network and Extreme Learning Machine (2015, methodology): “The obtained features are then combined to train an online sequential ELM (OS-ELM) [28], [29], [32], [33].”