Convex incremental extreme learning machine

By G. Huang, Lei Chen. Neurocomputing, 2007

1,121 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/464ebd4c86542e1610d67a9bc8810b8a7c109efe

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. Keyou You
5. Yuan Lan
6. Dianhui Wang
7. Hongming Zhou
8. Xiaojian Ding

In Electrical and Electronic Engineering

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

Citations in the corpus

• Extreme Learning Machine for Regression and Multiclass Classification (2012, background): “We conjecture that this may be true to the generalized SLFNs where the hidden layer may not be neuron alike [15], [16].”
• Extreme learning machines: a survey (2011, methodology): “I-ELMs can be implemented in different ways: 1.”
• Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning (2009, methodology): “Based on the universal approximation capability of SLFNs with random hidden nodes [4]–[ 7 ], Huangetal.”
• Trends in extreme learning machines: A review (2015, methodology): “…from the conventional neural networks learning tenet that hidden node parameters ( a i , b i ) need to be adjusted during training, ELM theories (Huang & Chen, 2007, 2008; Huang, Chen, et al., 2006) rigorously prove that hidden node parameters ( a i , b i ) can be randomly generated according…”
• Machine Learning Algorithms in Civil Structural Health Monitoring: A Systematic Review (2020, methodology): “For example, ELM was first proposed by in [52–55] as a tool that is faster in the training phase, which may result in better interpolation, but did not necessarily produce more precise and accurate results.”
• SeCoST: Sequential Co-Supervision for Weakly Labeled Audio Event Detection (2019, background): “The proposal derives ideas from two distinct, but partly related, learning paradigms — sequential learning [17] and knowledge sharing [18].”
• A fast pruned-extreme learning machine for classification problem (2008, background): “Note that the proof of universal approximation is shown to be valid for SLFNs with general type of hidden nodes, i.e., in the form of sigmoid, RBF or hybrid of both [8, 7 ].”
• Local Receptive Fields Based Extreme Learning Machine (2015, methodology): “a i In contrast to RVFL theories for semi-randomness, ELM theories show that i) Generally speaking, all the hidden node parameters can be randomly generated as long as the activation function is nonlinear piecewise continuous; ii) all the hidden nodes can be not only independent from training sample”