OP-ELM: Optimally Pruned Extreme Learning Machine

By Yoan Miché, Antti Sorjamaa, Patrick Bas, Olli Simula, Christian Jutten, Amaury Lendasse. IEEE Transactions on Neural Networks, 2010

773 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/066dd3d09eb5815e8be1da560abd1abe08f87cb9

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. Shiji Song
2. Gao Huang
3. G. Huang
4. Keyou You
5. J. Qiao
6. Hong-gui Han
7. Thangairulappan Kathirvalavakumar
8. Gethsiyal Augasta M

In Computer Vision and Pattern Recognition

1. Shiji Song
2. Gao Huang
3. G. Huang
4. J. Qiao
5. Hong-gui Han
6. Keyou You
7. Nan Liu
8. Zhiping Lin

Citations in the corpus

• Trends in extreme learning machines: A review (2015, methodology): “In TROP-ELM, the missing values are first replaced by their respective conditional means.”
• Short-term load forecasting based on multivariate time series prediction and weighted neural network with random weights and kernels (2018, methodology): “NNRW has been successfully applied to the function approximation [33], time series prediction [34,35], pattern classification [36,37] andotherfields [38].”
• Voting based extreme learning machine (2012, methodology): “In this subsection, simulations using V-ELM, SVM [12], OP-ELM [28], BP [9,24,27], and KNN [7,2] are conducted on all the above 19 datasets.”
• A structure optimisation algorithm for feedforward neural network construction (2013, methodology): “Many different pruning methods have been published in the research literature, for example, optimal brain surgeon (OBS) [13], optimally pruned extreme learning machine (OP-ELM) [14], subset-based training and pruning (SBTP) [15], independent component analysis (ICA) [16], extended Fourier amplitude ”
• NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search (2022, methodology): “OP-ELM [40] combines ELM, multiresponse sparse regression, and leave-one-out criterion to design single hidden layer feedforward networks.”
• A kernel machine-based secure data sensing and fusion scheme in wireless sensor networks for the cyber-physical systems (2016, methodology): “Motivated by [22], a novel scheme GM-OP-ELM through the combination of GM and optimally pruned extreme learning machine (OP-ELM) was proposed in [23].”
• Pruning algorithms of neural networks — a comparative study (2013, methodology): “The Pruning algorithms of neural networks -a comparative study feedforward neural network is by far the most popular architecture due to its structural flexibility, good representational capabilities, and the availability of a large number of training algorithms [3].”