Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning

Feng, Guorui; Huang, Guang-Bin; Lin, Qingping

doi:10.1109/tnn.2009.2024147

Cited by 578 publications

(53 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed adaptive OS-ELM based on improved ABC algorithm is compared with OS-ELM [26], EI-ELM [19], EM-ELM [11], and standard ELM [17]. The parameters of the proposed adaptive OS-ELM are as the follows: the data embedding dimension m is determined as 48, the number of neurons in the hidden It can be observed from Tab.…”

Section: Simulationmentioning

confidence: 99%

“…OS-ELM first calculates its initial network weights in the initial training stage, and then the corresponding network weights can be obtained on the basis of the initial network weights when a new training sample is added to the training sample set. However, OS-ELM and other improved ELM algorithms (I-ELM [18], EI-ELM [19], EM-ELM [11], and etc) believe that the importance of new and old training samples is the same, giving the same weight to old and new samples, and failing to highlight the role of new training samples. Moreover, as long as new training samples are obtained, OS-ELM updates the network weights recursively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fuzzy Multi-Objective Optimization Algorithms for Solving Multi-Mode Automated Guided Vehicles by Considering Machine Break Time and Artificial Neural Network

Nabovati¹,

Haleh²,

Vahdani³

2018

NNW

View full text Add to dashboard Cite

Abstract:As an improved algorithm of standard extreme learning machine, online sequential extreme learning machine achieves excellent classification and regression performance. However, online sequential extreme learning machine gives the same weight to the old and new training samples, and fails to highlight the importance of the new training samples. At the same time, the algorithm updates the network weights after obtaining the new training samples. This network weight updating mode lacks flexibility and increases unnecessary computation. This paper proposes an adaptive online sequential extreme learning machine with an effective sample updating mechanism. The new and old samples are given different weights. The effect of new training samples on the algorithm is further enhanced, which can further improve the regression prediction ability of extreme learning machine. At the same time, an improved artificial bee colony algorithm is proposed and used to optimize the parameters of the adaptive online sequential extreme learning machine. The stability and convergence property of proposed prediction method are proved. The actual collected short-term wind speed time series is used as the research object and verify the prediction perfromance of the proposed method. Multi step prediction simulation of short-term wind speed is performed out. Compared with other prediction methods, the simulation results show that the proposed approach has higher prediction accuracy and reliability performance, meanwhile improve the performance indicators.

show abstract

Section: Simulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fuzzy Multi-Objective Optimization Algorithms for Solving Multi-Mode Automated Guided Vehicles by Considering Machine Break Time and Artificial Neural Network

Nabovati¹,

Haleh²,

Vahdani³

2018

NNW

View full text Add to dashboard Cite

show abstract

“…A new algorithm of the I-ELM, called error minimized ELM (EM-ELM) is proposed at [12]. This network can add nodes one by one or group by group (Chunking).…”

Section: Incremental Based Extreme Learning Machinesmentioning

confidence: 99%

“…Lemma 1 [12]. Given an SLFN, let H 1 be the initial hidden layer output matrix with L 0 hidden nodes.…”

Section: Incremental Based Extreme Learning Machinesmentioning

confidence: 99%

Pseudoinverse Matrix Decomposition Based Incremental Extreme Learning Machine with Growth of Hidden Nodes

Kassani

Kim

2016

IJFIS

View full text Add to dashboard Cite

The proposal of this study is a fast version of the conventional extreme learning machine (ELM), called pseudoinverse matrix decomposition based incremental ELM (PDI-ELM). One of the main problems in ELM is to determine the number of hidden nodes. In this study, the number of hidden nodes is automatically determined. The proposed model is an incremental version of ELM which adds neurons with the goal of minimization the error of the ELM network. To speed up the model the information of pseudoinverse from previous step is taken into account in the current iteration. To show the ability of the PDI-ELM, it is applied to few benchmark classification datasets in the University of California Irvine (UCI) repository. Compared to ELM learner and two other versions of incremental ELM, the proposed PDI-ELM is faster.

show abstract

“…Theoretical proofs and a more thorough presentation of the ELM algorithm are detailed in the original paper in which Huang et al present the algorithm and its justifications [2]. Furthermore, the hidden nodes need not be 'neuron-alike' [10][11][12].…”

Section: Extreme Learning Machine (Elm)mentioning

confidence: 99%

Binary/ternary extreme learning machines

Heeswijk

Miché

2015

Neurocomputing

View full text Add to dashboard Cite

a b s t r a c tIn this paper, a new hidden layer construction method for Extreme Learning Machines (ELMs) is investigated, aimed at generating a diverse set of weights. The paper proposes two new ELM variants: Binary ELM, with a weight initialization scheme based on f0; 1g-weights; and Ternary ELM, with a weight initialization scheme based on fÀ1; 0; 1g-weights. The motivation behind this approach is that these features will be from very different subspaces and therefore each neuron extracts more diverse information from the inputs than neurons with completely random features traditionally used in ELM. Therefore, ideally it should lead to better ELMs. Experiments show that indeed ELMs with ternary weights generally achieve lower test error. Furthermore, the experiments show that the Binary and Ternary ELMs are more robust to irrelevant and noisy variables and are in fact performing implicit variable selection. Finally, since only the weight generation scheme is adapted, the computational time of the ELM is unaffected, and the improved accuracy, added robustness and the implicit variable selection of Binary ELM and Ternary ELM come for free.

show abstract

Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning

Cited by 578 publications

References 22 publications

Fuzzy Multi-Objective Optimization Algorithms for Solving Multi-Mode Automated Guided Vehicles by Considering Machine Break Time and Artificial Neural Network

Fuzzy Multi-Objective Optimization Algorithms for Solving Multi-Mode Automated Guided Vehicles by Considering Machine Break Time and Artificial Neural Network

Pseudoinverse Matrix Decomposition Based Incremental Extreme Learning Machine with Growth of Hidden Nodes

Binary/ternary extreme learning machines

Contact Info

Product

Resources

About