Architecture selection for networks trained with extreme learning machine using localized generalization error model

Wang, Xizhao; Shao, Qingyan; Miao, Qing; Zhai, Junhai

doi:10.1016/j.neucom.2011.12.053

Cited by 62 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, genetic representation of the FNN architecture as mentioned in Figs. 5(a), 5(b), 5(c) can be used for architecture optimization, which is equivalent to searching optimum architecture from a compact space of FNN topology [197,198]. Let us discuss the genetic representation of architecture in detail.…”

Section: Architecture Plus Weight Optimizationmentioning

confidence: 99%

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

414

154

View full text Add to dashboard Cite

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

show abstract

Section: Architecture Plus Weight Optimizationmentioning

confidence: 99%

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

414

154

View full text Add to dashboard Cite

show abstract

“…In supervised batch learning, the learning algorithms use a finite number of input-output samples for training [14][15][16][17][18]. For arbitrary distinct samples ( , ) ∈ × , where is a × 1 input vector and is a × 1 target vector, if an SLFN (single-hidden layer feedforward neural network [19][20][21][22][23][24]) with̃hidden nodes can approximate these samples with zero error, it then implies that there exists , , and , such that…”

Section: Kelm Algorithmmentioning

confidence: 99%

“…The regression model between the data matrix of piercing efficiency and the prediction valueŷ of piercing efficiency, which can be obtained by mean value substaged KELM-PLS method, is formula (15), and in the same way, the relational model between the data matrix of piercing energy consumption and the prediction valueŷ of piercing energy consumption, which can be obtained by substaged KELM-PLS method, is formula (16): 1 , 1,2 , . .…”

Section: Mean Value Substaged Kelm-pls Modelingmentioning

confidence: 99%

Modeling and Optimization for Piercing Efficiency and Energy Consumption Based on Mean Value Substaged KELM-PLS and GA Method

Xiao

Wang

2014

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Piercing manufacture of seamless tubes is the process that pierces solid blank into tube hollow. Piercing efficiency and energy consumption are the important indexes in the production of seamless tubes. Piercing process has the multivariate, nonlinear, cross-coupling characteristics. The complex factors that affect efficiency and consumption make it difficult to establish the mechanism models for optimization. Based on the production process, this paper divides the piercing process into three parts and proposes the piercing efficiency and energy consumption prediction models based on mean value staged KELM-PLS method. On the basis of mean value staged KELM-PLS prediction model, the minimum piercing energy consumption and maximum piercing efficiency are calculated by genetic optimization algorithm. Simulation and experiment prove that the optimization method based on the piercing efficiency and energy consumption prediction model can obtain the optimal process parameters effectively and also provide reliable evidences for practical production.

show abstract

“…As a novel learning technique, extreme learning machines (ELM) has been demonstrated with its outstanding performance in training speed, prediction accuracy, and generalization ability [7], [8]. Several IPSs have already leveraged ELM to deliver accurate location estimation with fast training speed [1], [9], [10].…”

Section: Introductionmentioning

confidence: 99%

Robust Extreme Learning Machine With its Application to Indoor Positioning

Zou

Zhou

et al. 2016

IEEE Trans. Cybern.

101

View full text Add to dashboard Cite

The increasing demands of location-based services have spurred the rapid development of indoor positioning system and indoor localization system interchangeably (IPSs). However, the performance of IPSs suffers from noisy measurements. In this paper, two kinds of robust extreme learning machines (RELMs), corresponding to the close-to-mean constraint, and the small-residual constraint, have been proposed to address the issue of noisy measurements in IPSs. Based on whether the feature mapping in extreme learning machine is explicit, we respectively provide random-hidden-nodes and kernelized formulations of RELMs by second order cone programming. Furthermore, the computation of the covariance in feature space is discussed. Simulations and real-world indoor localization experiments are extensively carried out and the results demonstrate that the proposed algorithms can not only improve the accuracy and repeatability, but also reduce the deviation and worst case error of IPSs compared with other baseline algorithms.

show abstract

Architecture selection for networks trained with extreme learning machine using localized generalization error model

Cited by 62 publications

References 24 publications

Metaheuristic design of feedforward neural networks: A review of two decades of research

Metaheuristic design of feedforward neural networks: A review of two decades of research

Modeling and Optimization for Piercing Efficiency and Energy Consumption Based on Mean Value Substaged KELM-PLS and GA Method

Robust Extreme Learning Machine With its Application to Indoor Positioning

Contact Info

Product

Resources

About