Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Extreme learning machine”

Extreme Learning Machine

Discriminative Graph Regularized, Jia-yi Zhu, Wei-long Zheng et al. · 2015

Abstract—This study aims at finding the relationship be-tween EEG signals and human emotional states. Movie clips are used as stimuli to evoke positive, neutral and negative emotions of subjects. We introduce a new effective classifier named discriminative graph regularized extreme learning machine (GELM) for EEG-based emotion recognition. The average classification accuracy of GELM using differential entropy (DE) features on the whole five frequency bands is 80.25%, while the accuracy of SVM is 76.62%. These results indicate that GELM is more suitable for emotion recognition than SVM. Additionally, the accuracies of GELM using DE features on Beta and Gamma bands are 79.07%, 79.93 % respectively. This suggests that these two bands are more relevant to emotion. The experimental results indicate that the EEG patterns for emotion are generally stable among different experiments and subjects. By using minimal-redundancy-maximal-relevance (MRMR) al-gorithm and correlation coefficients to select effective features, we get the distribution of top 20 subject-independent features and build a manifold model to monitor the trajectory of emotion changes with time. I.

Cited by 0

Incremental extreme learning machine

Lei Chen · 2007

Feedforward neural networks have attracted considerable attention in many fields mainly due to their approximation capability, i.e., neural networks can accurately approximate target functions with a finite number of neurons 1 .

Cited by 1Open access

Optimized Extreme Learning Machine

Roshan Kaloni, Tejas R Nayak, Mitanshu Sankhe et al. · International Journal for Research in Applied Science and Engineering Technology · 2022

Abstract: Extreme Learning Machine (ELM) is a learning method for single-hidden layer feedforward neural network (SLFN) training. The ELM strategy speeds up learning by generating input weights and biases for hidden nodes at random rather than modifying network parameters, making it much faster than the standard gradient-based approach. In this project, an ELM optimized by Hybrid Particle Swarm Optimization approach is presented to optimize the input weights and hidden biases for ELM. We will analyze and obtain results for benchmark datasets. The Optimized Extreme Learning Machine algorithm's output is compared to publicly available data. Later we will compare different algorithms and check which one gives better output metrics. Keywords: ELM, SLFN, PSO, Gradient-based approach, Optimization

Cited by 0Open access

Iterative Extreme Learning Machine

Boonnithi Jiramaneepinit, Ukrit Watchareeruetai · 2018

This paper proposes a simple but effective method to improve the generalization performance of extreme learning machine (ELM), which is an extremely fast learning method for a single-hidden-layer feedforward neural network (SLFN). The proposed method adopts an online sequential learning technique to update the output weight matrix of a learned SLFN by using misclassified training samples. As the process of updating these weights could be iteratively performed, the proposed method is named iterative ELM (I-ELM). The proposed I-ELM was evaluated on three datasets, including MNIST, Small NORB, and CIFAR-10, and compared with the standard ELM. Experimental results indicate that by using only a few iterations, the proposed I-ELM could effectively improve the generalization performance of SLFNs.

Cited by 0

Regularized Extreme Learning Machine

Wanyu Deng, Qinghua Zheng, Chen Lin · 2009

Extreme learning machine proposed by Huang G-B has attracted many attentions for its extremely fast training speed and good generalization performance. But it still can be considered as empirical risk minimization theme and tends to generate over-fitting model. Additionally, since ELM doesn't considering heteroskedasticity in real applications, its performance will be affected seriously when outliers exist in the dataset. In order to address these drawbacks, we propose a novel algorithm called regularized extreme learning machine based on structural risk minimization principle and weighted least square. The generalization performance of the proposed algorithm was improved significantly in most cases without increasing training time.

Cited by 456

Functional extreme learning machine

Xianli Liu, Guo Zhou, Yongquan Zhou et al. · Frontiers in Computational Neuroscience · 2023

The standard data sets UCI and StatLib are selected for regression problems, and compared with the ELM, support vector machine (SVM) and other algorithms, the experimental results show that the FELM achieves better performance.

Cited by 10Open access

Sequential learning for extreme learning machine

Nanying Liang · 2006

The approximation capability of feedforward neural networks has been deeply studied, and it has been shown that the neural network with as few as a single hidden layer is a universal approximator. We refer such neural networks as Single hidden Layer Feedforward Neural networks (SLFNs). Depending on the kind of activation function used in the hidden layer, two popular structures of SLFNs can be recognized in the literature: SLFNs with ridge activation function, and SLFNs with radial basis activation function: radial basis function neural networks (RBF-NNs). By recognizing the need for sequential learning in practice, we lay the foundation of the thesis on sequential learning algorithm design for SLFNs. Traditional sequential algorithms for training SLFNs with ridge activation function are referred to as stochastic BP-based algorithms. For training RBF-NNs, they are referred to as RAN-based algorithms. However, the intrinsic drawbacks of these sequential learning algorithms prohibit their applications into complicate and large-scale problems. This motivates us to propose a novel method, which is referred to as Online Sequential Extreme Learning Machine (OS-ELM) in the thesis. OS-ELM is derived from batch Extreme Learning Machine (ELM) on the basis of recursive least-squares (RLS) algorithm. The resulted sequential algorithm trains both SLFNs with ridge function and RBF-NNs in a unified framework. Additionally it can operate in the learning mode of one-by-one as well as chunk-by-chunk.

Cited by 1Open access

Pre-trained extreme learning machine

Zhang, Y, Wu, J, Cai, Z et al. · UTS ePRESS (University of Technology Sydney) · 2017

© Springer International Publishing AG 2017. Extreme learning machine (ELM) is a promising learning method for training “generalized” single hidden layer feedforward neural networks (SLFNs), which has attracted significant interest recently for its fast learning speed, good generalization ability and ease of implementation. However, due to its manually selected network parameters (e.g., the input weights and hidden biases), the performance of ELM may be easily deteriorated. In this paper, we propose a novel pre-trained extreme learning machine (P-ELM for short) for classification problems. In P-ELM, the superior network parameters are pre-trained by an ELM-based autoencoder (ELM-AE) and embedded with the underlying data information, which can improve the performance of the proposed method. Experiments and comparisons on face image recognition and handwritten image annotation applications demonstrate that P-ELM is promising and achieves superior results compared to the original ELM algorithm and other ELM-based algorithms.

Cited by 0

Extreme learning machine web portal

Ong, Jasmine Jiemin. · DR-NTU (Nanyang Technological University) · 2013

There has been many research and applications of the algorithm on Extreme Learning Machines (ELM). However, there is no platform which allows researchers or users to easily access these information from a direct web portal. With a web portal in place for ELM, people can better understand on the topic of ELM, as well as finding all the resources available on this technique from one common source. Also, this web portal will provide the means for sharing resources to the administrators, such as conference/journal materials and software codes.
\n
\nIn this project, the web portal was built on MAMP (Apache, MYSQL, PHP) and the entire design and development of the web portal is through the use of industrial-standard software such as Adobe Photoshop CS5.5, Adobe Dreamweaver CS5.5 and through the use of web programming language which includes PHP, Javascript, HTML and CSS.
\n
\nThe development of the web portal consists of a few stages – Preparation (Chapter 1 – Chapter 4), design of web portal (Chapter 5), implementation of web portal (Chapter 6 – Chapter 8) and the testing of web portal (Chapter 9).

Cited by 0

Photonic quantum extreme learning machine

Alessia Suprano, Danilo Zia, Luca Innocenti et al. · Quantum 2.0 Conference and Exhibition · 2024

We experimentally implemented a quantum extreme learning machine to re-construct the polarization state of single photons. Our approach offers a resource-efficient method that does not require a detailed apparatus calibration.

Cited by 0

Classification Using Extreme Learning Machine

Sahoo, Soumya, Mohapatra, Sunil Kumar, Panda, Bijayalaxmi · Zenodo (CERN European Organization for Nuclear Research) · 2013

Extreme Learning Machine (ELM) has become popular for solving classification problem due to its fast speed. The performance of ELM often relies on random input hidden node parameters. Neural network also uses artificial intelligence by adjusting weights and minimizing the error. The learning speed of feedforward neural network is very slow. Due to two slow gradient-based learning algorithms and iterative tuning of various parameters. This paper presents a comparative study of back propagation algorithm and an extremely fast ELM technique for single layer feedforward neural network which takes random hidden nodes and determines the output weights without iterative tuning. In theory, this algorithm tends to provides better performance at extremely fast learning speed.

Cited by 0Open access

Genetically optimized extreme learning machine

Tiago Matias, Rui Araújo, Carlos Henggeler Antunes et al. · 2013

This paper proposes a learning algorithm for single-hidden layer feedforward neural networks (SLFN) called genetically optimized extreme learning machine (GO-ELM). In the GO-ELM, the structure and the parameters of the SLFN are optimized by a genetic algorithm (GA). The output weights, like in the batch ELM, are obtained by a least squares algorithm, but using Tikhonov's regularization in order to improve the SLFN performance in the presence of noisy data. The GA is used to tune the set of input variables, the hidden-layer configuration and bias, the input weights and the Tikhonov's regularization factor. The proposed method was applied and compared with four other methods over five benchmark problems available in a public repository. Besides it was applied in the estimation of the temperature at the burning zone of a real cement kiln plant.

Cited by 13