Extreme learning machine: RBF network case

By G. Huang, Chee Kheong Siew. ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004., 2004

310 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/3b2c67905dfa03e3624a5db4a14e3d7fded478d1

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. Lei Chen
3. Yuan Lan
4. Dianhui Wang
5. Chee Kheong Siew
6. Yiqiang Chen
7. Qin-Yu Zhu
8. Yang Gu

In Electrical and Electronic Engineering

1. G. Huang
2. Lei Chen
3. Yuan Lan
4. Dianhui Wang
5. Chee Kheong Siew
6. Yiqiang Chen
7. Qin-Yu Zhu
8. Yang Gu

Citations in the corpus

• Enhanced random search based incremental extreme learning machine (2008, methodology): “The activation functions used in ELM include differentiable [11,13,14] and nondifferentiable [12] functions, continuous [11,13,14] and noncontinuous [12] functions, etc.”
• 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].”
• Extreme learning machines: a survey (2011, background): “4 means that ELM with fixed network architectures [5, 6, 35, 36] where the output parameters are determined by ordinary least square can work as universal approximators if only the activation function g is nonconstant piecewise and spanfGða; b; xÞ : ða; bÞ 2 R Rg is dense in L(2).”
• Extreme learning machine: Theory and applications (2006, background): “It may also be interesting to further compare ELM with sigmoidal activation functions and ELM with RBF activation functions [13,14] in the future work.”
• Semi-supervised deep extreme learning machine for Wi-Fi based localization (2015, background): “The other reason is that crowd sourcing [37,38] is adopted for data collection, so the variance of RSS (fingerprint) not only comes from the changing environment, but also results in the variance of devices.”
• Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes (2006, background): “Furthermore, Huang et al. [12], [13] show that the centers and impact factors of the RBF nodes of RBF networks can also be randomly chosen.”