Journal ArticleDOI
Representational learning with ELMs for big data
TLDR
Huang et al. as mentioned in this paper proposed ELM-AE, a special case of ELM, where the input is equal to output, and the randomly generated weights are chosen to be orthogonal.Abstract:
Geoffrey Hinton and Pascal Vincent showed that a restricted Boltzmann machine (RBM) and auto-encoders (AE) could be used for feature engineering. These engineered features then could be used to train multiple-layer neural networks, or deep networks. Two types of deep networks based on RBM exist: the deep belief network (DBN)1 and the deep Boltzmann machine (DBM). Guang-Bin Huang and colleagues introduced the extreme learning machine (ELM) as an single-layer feed-forward neural networks (SLFN) with a fast learning speed and good generalization capability. The ELM for SLFNs shows that hidden nodes can be randomly generated. ELM-AE output weights can be determined analytically, unlike RBMs and traditional auto-encoders, which require iterative algorithms. ELM-AE can be seen as a special case of ELM, where the input is equal to output, and the randomly generated weights are chosen to be orthogonal.read more
Citations
More filters
Proceedings ArticleDOI
Modelling retinal ganglion cells using self-organising fuzzy neural networks
TL;DR: Fuzzy neural network techniques are used to accurately model the responses of retinal ganglion cells and are illustrated how a self-organising fuzzy neural network can accurately model ganglions cell behaviour, and are a viable alternative to traditional system identification techniques.
Journal ArticleDOI
Evolutionary Hierarchical Sparse Extreme Learning Autoencoder Network for Object Recognition
Yujun Zeng,Lilin Qian,Junkai Ren +2 more
TL;DR: A novel sparse autoenCoder derived from ELM and differential evolution is proposed and integrated into a hierarchical hybrid autoencoder network to accomplish the end-to-end learning with raw visible light camera sensor images and applied to several typical object recognition problems.
Journal ArticleDOI
Multilayer Graph Node Kernels: Stacking While Maintaining Convexity
TL;DR: A new family of kernels for graphs which exploits an abstract representation of the information inspired by the multilayer perceptron architecture through a series of stacked kernel pre-image estimators, trained in an unsupervised fashion via convex optimization.
Journal ArticleDOI
Unsupervised feature learning with sparse Bayesian auto-encoding based extreme learning machine
TL;DR: A sparse Bayesian learning scheme is introduced into ELM-AE for better generalization capability and pruning hidden nodes for better performance and efficiency according to estimated variances of prior distribution of output weights is achieved.
Journal ArticleDOI
Adding reliability to ELM forecasts by confidence intervals
Anton Akusok,Andrey Gritsenko,Yoan Miche,Kaj-Mikael Björk,Rui Nian,Paula Lauren,Amaury Lendasse +6 more
TL;DR: This method provides CIs for ELM predictions by estimating standard deviation of a random output for a particular input sample, and shows good results on both toy and real skin segmentation datasets, and compares well with the existing Confidence-weighted ELM methods.
References
More filters
Journal ArticleDOI
Extreme learning machine: Theory and applications
TL;DR: A new learning algorithm called ELM is proposed for feedforward neural networks (SLFNs) which randomly chooses hidden nodes and analytically determines the output weights of SLFNs which tends to provide good generalization performance at extremely fast learning speed.
Journal ArticleDOI
Extreme Learning Machine for Regression and Multiclass Classification
TL;DR: ELM provides a unified learning platform with a widespread type of feature mappings and can be applied in regression and multiclass classification applications directly and in theory, ELM can approximate any target continuous function and classify any disjoint regions.
Journal ArticleDOI
Universal approximation using incremental constructive feedforward networks with random hidden nodes
TL;DR: This paper proves in an incremental constructive method that in order to let SLFNs work as universal approximators, one may simply randomly choose hidden nodes and then only need to adjust the output weights linking the hidden layer and the output layer.
Journal ArticleDOI
Optimization method based extreme learning machine for classification
TL;DR: Under the ELM learning framework, SVM's maximal margin property and the minimal norm of weights theory of feedforward neural networks are actually consistent and ELM for classification tends to achieve better generalization performance than traditional SVM.