Tensor Decomposition Based Approach for Training Extreme Learning Machines

Nair, Nikhitha K.; Asharaf, S.

doi:10.1016/j.bdr.2017.07.002

Cited by 8 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This MNIST handwritten dataset is analyzed in three different datasets such as sine, tribas and sigmoid. Table 2 and Fig 3 shows that the AR-ELM training time for MNIST handwritten dataset is less when compared to the existing methods such as basic ELM [21], ELM-TUCKER [21] and ELM-PARAFAC [21]. The training time of the Basic ELM [21] is high than the other methods.…”

Section: Performance Analysis Of Mnist Handwritten Datasetmentioning

confidence: 94%

“…The Table 3 and Fig 4 shows that the AR-ELM training time for the KDD Cup 1999 dataset is less when compared to the existing methods such as basic ELM [21], ELM-TUCKER [21] and ELM-PARAFAC [21]. Due to the high amount of samples of the KDDCup99 data (i.e., above 60000), the training process of the ELM [21] takes more time. Similarly, the training time of the ELM-TUCKER [21] and ELM-PARAFAC [21] also higher than the AR-ELM.…”

Section: Performance Analysis Of Kdd Cup 1999 Datasetmentioning

confidence: 99%

“…N.K. Nair and S. Asharaf, [21] presented the tensor decomposition based ELM by considering two different decomposition methods such as TUCKER and PARAFAC (parallel factor analysis). The TUCKER decomposition is a generalized version of the canonical decomposition.…”

Section: Literature Surveymentioning

confidence: 99%

“…Due to the high amount of samples of the KDDCup99 data (i.e., above 60000), the training process of the ELM [21] takes more time. Similarly, the training time of the ELM-TUCKER [21] and ELM-PARAFAC [21] also higher than the AR-ELM.…”

Section: Performance Analysis Of Kdd Cup 1999 Datasetmentioning

confidence: 99%

See 3 more Smart Citations

Automotive Rank Based ELM Using Iterative Decomposition

Nagelli¹,

Ragala²,

B³

2019

IJIES

View full text Add to dashboard Cite

Nowadays, the Extreme learning machine (ELM) is playing a key role in machine intelligence and big data analytics due to its various advantages such as fast training rate, universal classification/regression and the capability of approximation. The standard ELM uses the Moore-Penrose generalized pseudo-inverse for solving the hidden layer activation matrix and also it identifies the output weights. Because of that, the standard ELM takes more time to train the features from the dataset. In ELM, scalability also considered as a one of the major concern while processing the large dataset. In order to overcome this concern, the Automotive Rank based ELM (AR-ELM) is proposed to obtain an effective tensor decomposition for diminishing the training time. Besides, the Bayesian approach is considered in this AR-ELM to remove the redundancy from the decomposed samples of the tensor. The major objective of this proposed AR-ELM is to process the large amount of dataset without depending on memory capacities. The recognition accuracy is improved by eliminating redundant information. The key idea of the AR-ELM is to reduce the training time while processing the huge dataset. The implementation and simulation of the AR-ELM is done in Spark Python 3.7. The performance of the AR-ELM is analysed in terms of accuracy, precision, recall and training time. The proposed methodology is compared with three existing methodologies such as basic ELM, ELM-TUCKER and ELM-PARAFAC. The recognition accuracy of the AR-ELM methodology with Hardlims activation function is 0.8879 for letter recognition dataset, it is high when compared to the basic ELM, ELM-TUCKER and ELM-PARAFAC that are 0.8102, 0.8375 and 0.834 respectively.

show abstract

Section: Performance Analysis Of Mnist Handwritten Datasetmentioning

confidence: 94%

Section: Performance Analysis Of Kdd Cup 1999 Datasetmentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

Section: Performance Analysis Of Kdd Cup 1999 Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Automotive Rank Based ELM Using Iterative Decomposition

Nagelli¹,

Ragala²,

B³

2019

IJIES

View full text Add to dashboard Cite

show abstract

“…In general, there have been great efforts in adapting ELM to tensorial inputs by applying certain matrix/tensor decomposition techniques [8], which are usually empirical. In this paper, we propose a novel Manuscript ELM model with tensorial inputs (TELM) to extend the traditional ELM models for tensorial contexts while retaining the valuable ELM features.…”

Section: Introductionmentioning

confidence: 99%

Multi-Antenna Channel Interpolation via Tucker Decomposed Extreme Learning Machine

Zhang

et al. 2019

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Channel interpolation is an essential technique for providing high-accuracy estimation of the channel state information (CSI) for wireless systems design where the frequency-space structural correlations of multi-antenna channel are typically hidden in matrix or tensor forms. In this letter, a modified extreme learning machine (ELM) that can process tensorial data, or ELM model with tensorial inputs (TELM), is proposed to handle the channel interpolation task. The TELM inherits many good properties from ELMs. Based on the TELM, the Tucker decomposed extreme learning machine (TDELM) is proposed for further improving the performance. Furthermore, we establish a theoretical argument to measure the interpolation capability of the proposed learning machines. Experimental results verify that our proposed learning machines can achieve comparable mean squared error (MSE) performance against the traditional ELMs but with 15% shorter running time, and outperform the other methods for a 20% margin measured in MSE for channel interpolation. Index TermsChannel interpolation, extreme learning machine, tensor decomposition.

show abstract