2011
DOI: 10.1109/tnn.2010.2103956
|View full text |Cite
|
Sign up to set email alerts
|

BELM: Bayesian Extreme Learning Machine

Abstract: The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other appro… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
69
0
1

Year Published

2011
2011
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 147 publications
(70 citation statements)
references
References 11 publications
0
69
0
1
Order By: Relevance
“…After Huang et al proposed the ELM algorithm, it was applied widely in computational intelligence and machine learning [11][12][13][14][15][16]. However, ELM may cause overfitting when it computes an output for high-dimensional data.…”
Section: Extreme Learning Machinementioning
confidence: 99%
“…After Huang et al proposed the ELM algorithm, it was applied widely in computational intelligence and machine learning [11][12][13][14][15][16]. However, ELM may cause overfitting when it computes an output for high-dimensional data.…”
Section: Extreme Learning Machinementioning
confidence: 99%
“…As generalization, the asymptotic stability of a certain class of integrated semigroups is discussed by means of Lyapunov functionals [12]. In this case, we obtain the exponentially bounded behavior in the sense that for and (where K denotes n factorial) (16) The possible interconnection between of the equilibrium and of the anomalous transport has been discussed.…”
Section: Ifmentioning
confidence: 99%
“…These methods introduce a probability distribution on the network parameters and the committed errors. The Bayesian ELM has the advantages of both ELM and Bayesian models [16].…”
Section: Fuzzy Bayesian Computationmentioning
confidence: 99%
“…Recently, [13] proposed a Bayesian methodology dubbed the Bayesian ELM (BELM). Their method relies on the utilization of Bayesian linear regression as a means of obtaining a posterior distribution over the columns w j of the trainable weights matrices W .…”
Section: Relations To Existing Modelsmentioning
confidence: 99%
“…Indeed, if we consider a kernel of the form (11), the resulting expression of K r (X, X) will turn out to be essentially low-rank by construction: Expanding (16) and (17) in terms of K r (X, X) and x(t), and using the matrix inversion lemma, the expressions of the 1HNBKM predictive mean and variance can be restated in the forms (19) and (20), respectively. Therefore, our approach comprises a generalization of the BELM network [13], incorporates it as a special case, and reduces to it when a linear kernel function is considered.…”
Section: Relations To Existing Modelsmentioning
confidence: 99%