Optimization method based extreme learning machine for classification

By G. Huang, Xiaojian Ding, Hongming Zhou. Neurocomputing, 2010

872 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/b5ae39d8bf8a06ae91b236ef115fdab8921e6455

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 naive Bayes probability estimation model based on self-adaptive differential evolution (2014, methodology): “…using 36 UCI data sets (Merz et al. 1997), which are considered as benchmark data sets for data mining and machine learning related classification algorithms (Flores et al. 2009; Huang et al. 2010; Jiang 2011; Jiang et al. 2012a; Su et al. 2008), to validate the effectiveness of our new algorithm.”
A Hybrid Feature Extraction Method With Regularized Extreme Learning Machine for Brain Tumor Classification (2019, positive): “Initializing the weights and biases of the input layer is randomly selected before going to compute the weights of the output layer [23, 24]”
Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects (2019, methodology): “ELM represents a learning method that is suitable for multi-class classification, due to its multi-input structure and single-hidden feed-forward networks, achieving better performance compared to SVM [51].”
Trends in extreme learning machines: A review (2015, methodology): “…Schmidt, Kraaijveld, & Duin, 1992; White, 1989, 2006), in essence the original 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…”
Weighted extreme learning machine for imbalance learning (2013, result): “From optimization point of view, connections between ELM and the popular support vector machines (SVMs) exist mainly in the aspects of problem formulation, network architecture except that solutions of SVMs are suboptimal compared to those of ELM [5,6].”
Extreme learning machines: a survey (2011, methodology): “Experimental results [6, 39, 92] show that compared to backpropagation algorithm, SVM and least-square SVM (LS-SVM) ELM usually achieve similar or better generalization in regression and classification applications.”
Local Receptive Fields Based Extreme Learning Machine (2015, methodology): “A popular and efficient closed-form solution for ELM with p q 2 1 2 v v = = = = [12], [42], [44] is:”
Machine Learning for 5G/B5G Mobile and Wireless Communications: Potential, Limitations, and Future Directions (2019, background): “Underfitting takes place when the model is not able to obtain a low error on the training set, whereas overfitting occurs when there is a significant difference between the training error and test error [38].”
Using spectral reflectance to estimate leaf chlorophyll content of tea with shading treatments (2018, background): “(Huang et al. 2010) showed that the extreme learning machine has less 378 optimisation constraints and its superiorities have been confirmed in regression (Maliha et al.”
A review on extreme learning machine (2021, methodology): “Comparedwith support vector machine (SVM) [23], ELM tends to yield better classification performancewith less optimization constrains [55].”
Extreme Learning Machine for Regression and Multiclass Classification (2012, methodology): “Huang et al. [29] use random kernels and discard the term bias b used in the conventional SVM.”