Optimization method based extreme learning machine for classification

Huang, Guang-Bin; Ding, Xiaoqing; Zhou, Hongming

doi:10.1016/j.neucom.2010.02.019

Cited by 800 publications

(380 citation statements)

References 16 publications

Supporting

Mentioning

348

Contrasting

Unclassified

Order By: Relevance

“…According to [25,26,32], the non-trained random weights, in combination with the MSE optimization criterion, reduces the chance of overfitting the training data in RCNs and ELMs and hence, let the system generalize better to noisy data than a system with fully trained parameters. In what follows, we distinguish two experimental settings: one in which the system is trained on clean images only (clean training) and one in which the system is trained on a mix of clean samples and samples corrupted by the five noise types that are also present in the test set (multi-conditional training).…”

Section: Recognition Of Noisy Imagesmentioning

confidence: 99%

On the application of reservoir computing networks for noisy image recognition

et al. 2018

View full text Add to dashboard Cite

Reservoir Computing Networks (RCNs) are a special type of single layer recurrent neural networks, in which the input and the recurrent connections are randomly generated and only the output weights are trained. Besides the ability to process temporal information, the key points of RCN are easy training and robustness against noise. Recently, we introduced a simple strategy to tune the parameters of RCNs. Evaluation in the domain of noise robust speech recognition proved that this method was effective. The aim of this work is to extend that study to the field of image processing, by showing that the proposed parameter tuning procedure is equally valid in the field of image processing and conforming that RCNs are apt at temporal modeling and are robust with respect to noise. In particular, we investigate the potential of RCNs in achieving competitive performance on the well-known MNIST dataset by following the aforementioned parameter optimizing strategy. Moreover, we achieve good noise robust recognition by utilizing such a network to denoise images and supplying them to a recognizer that is solely trained on clean images. The experiments demonstrate that the proposed RCN-based handwritten digit recognizer achieves an error rate of 0.81 percent on the clean test data of the MNIST benchmark and that the proposed RCN-based denoiser can effectively reduce the error rate on the various types of noise.

show abstract

Section: Recognition Of Noisy Imagesmentioning

confidence: 99%

On the application of reservoir computing networks for noisy image recognition

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Compared with traditional popular gradient-based learning algorithms for SLFNs, ELM not only learns much faster with higher generalization ability but also avoids many difficulties associated with stopping criteria, learning rates, learning epochs, and local minima. The ELM model has been used in many areas, such as time series prediction [44,45], image quality assessment [46], classification [47,48], face recognition [49,50] and others. The structure of ELM is illustrated in Fig.…”

Section: Principle Of Extreme Learning Machinementioning

confidence: 99%

Influencing factor analysis and displacement prediction in reservoir landslides − a case study of Three Gorges Reservoir (China)

Huang

Yin

et al. 2016

Teh. vjesn.

View full text Add to dashboard Cite

Subject reviewThe developmental tendencies of cumulative displacement time series associated with reservoir landslides influenced by large water reservoirs must be effectively predicted. However, traditional methods do not encompass the dynamic response relationships between landslide deformation and its influencing factors. Therefore, a new approach based on the exponential smoothing (ES) and multivariate extreme learning machine methods was introduced to reveal the influencing factors of landslide deformation and to forecast landslide displacement values. First, the influencing factors of reservoir landslide deformation were analysed. Second, the ES method was used to predict the trend term displacement and obtain the periodic term displacement by determining the trend term from the cumulative displacement. Next, multivariate influencing factors were analysed to explain the periodic term displacement. Then, an extreme learning machine (ELM) model was established to predict the periodic term displacement based on the multivariable analysis of influencing factors. Finally, cumulative displacement prediction values were obtained by adding the trend and periodic displacement prediction values. The Bazimen and Baishuihe landslides in Three Gorges Reservoir Area (TGRA) were selected as case studies. The proposed ES-multivariate ELM (ES-MELM) model was compared to the ES-univariate ELM (ES-ELM) model. The results show that reservoir landslide deformation is mainly influenced by periodic reservoir water level fluctuations and heavy rainfall. Additionally, the proposed model yields more accurate predictions than the ES-ELM model. Keywords: displacement prediction; exponential smoothing; Extreme Learning Machine; multivariate influencing factors; reservoir landslide; Three Gorges ReservoirAnaliza faktora utjecaja i predviđanje pomaka klizišta akumulacije -studija slučaja Three Gorges Reservoir (Kina)Pregledni članak Potrebno je učinkovito predviđati kako će se vremenski odvijati kumulativni pomaci povezani s klizištima akumulacija. Međutim, tradicionalne metode ne obuhvaćaju dinamički uspostavljene odnose između deformacije klizišta i faktora koji na to utječu. Dakle, uveden je novi pristup na temelju eksponencijalnog izglađivanja (EI) i multivarijatnih metoda ekstremno učećeg stroja kako bi se otkrili čimbenici od utjecaja na deformacije klizišta i predvidjele vrijednosti pomaka klizišta. Prvo su analizirani faktori koji utječu na deformacije klizišta akumulacije. Zatim je EI postupak rabljen za predviđanje trajanja trenda pomaka i dobivanje trajanja periodičnog pomaka određivanjem trajanja trenda iz kumulativnog pomaka. Dalje, analizirani su multivarijatni utjecajni faktori kako bi objasnili trajanje periodičnog pomaka. Nakon toga, postavljen je model ekstremno učećeg stroja kako bi se predvidjelo trajanje periodičnog pomaka na temelju multivarijatne analize utjecajnih čimbenika. Konačno, dobivene su vrijednosti predviđanja kumulativnog pomaka dodavanjem vrijednosti predviđanja trenda i periodičnog pomaka. Bazimen i B...

show abstract

“…ELM for classification is easily implemented and less sensitive to specified parameters [32]. In ELM, the hidden nodes of the single hidden layer feedforward networks (SLFNs) can be randomly generated and the output weights of SLFNs are analytically determined [33]. Given N distinct samples(x k ,t k ), where…”

Section: Classifiermentioning

confidence: 99%

Classification of Hemodynamic Responses Associated With Force and Speed Imagery for a Brain-Computer Interface

Yin

Jiang

et al. 2015

J Med Syst

View full text Add to dashboard Cite

Functional near-infrared spectroscopy (fNIRS) is an emerging optical technique, which can assess brain activities associated with tasks. In this study, six participants were asked to perform three imageries of hand clenching associated with force and speed, respectively. Joint mutual information (JMI) criterion was used to extract the optimal features of hemodynamic responses. And extreme learning machine (ELM) was employed to be the classifier. ELM solved the major bottleneck of feedforward neural networks in learning speed, this classifier was easily implemented and less sensitive to specified parameters. The 2-class fNIRS-BCI system was firstly built with an average accuracy of 76.7 %, when all force and speed tasks were categorized as one class, respectively. The multi-class systems based on different levels of force and speed attempted to be investigated, the accuracies were moderate. This study provided a novel paradigm for establishing fNIRS-BCI system, and provided a possibility to produce more degrees of freedom in BCI system.

show abstract

Optimization method based extreme learning machine for classification

Cited by 800 publications

References 16 publications

On the application of reservoir computing networks for noisy image recognition

On the application of reservoir computing networks for noisy image recognition

Influencing factor analysis and displacement prediction in reservoir landslides − a case study of Three Gorges Reservoir (China)

Classification of Hemodynamic Responses Associated With Force and Speed Imagery for a Brain-Computer Interface

Contact Info

Product

Resources

About