Hierarchical Extreme Learning Machine for unsupervised representation learning

Zhu, Wentao; Miao, Jun; Qing, Laiyun; Huang, Guang-Bin

doi:10.1109/ijcnn.2015.7280669

Cited by 50 publications

(36 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ELM can be implemented in different methods like classification, compression and spare coding in different methods, due to which multi-ELMs are used for the formation of multi-hidden layer network, deep learning, or hierarchical networks [37][38][39]. Gocken et al developed an improved ELM model [40] consisting of an integration of GA, DE, PSO and weighted superposition attraction (WSA).…”

Section: Elmmentioning

confidence: 99%

Applications of neural network based methods on stock market prediction: survey

Mohapatra¹,

Das²,

Das³

et al. 2018

IJET

View full text Add to dashboard Cite

Financial forecasting is one of the domineering fields of research, where investor's money is at stake due to the rise or fall of the stock prices which unpredictable and fluctuating. Basically as the demand for stock markets has been rising at an unprecedented rate so its prediction becomes all the more exciting and challenging. Prediction of the forthcoming stock prices mostly Artificial Neural Network (ANN) based models are taken into account. The other models such as Bio-inspired Computing, Fuzzy network model etc., considering statistical measures, technical indicators and fundamental indicators are also explored by the researchers in the field of financial application. Ann's development has led the investors for hoping the best prediction because networks included great capability of machine learning such as classification and prediction. Most optimization techniques are being used for training the weights of prediction models. Currently, various models of ANN-based stock price prediction have been presented and successfully being carried to many fields of Financial Engineering. This survey aims to study the mostly used ANN and related representations on Stock Market Prediction and make a proportional analysis between them.

show abstract

Section: Elmmentioning

confidence: 99%

Applications of neural network based methods on stock market prediction: survey

Mohapatra¹,

Das²,

Das³

et al. 2018

IJET

View full text Add to dashboard Cite

show abstract

“…First, consider the DELM with kernel based on ELM-AE algorithm (DELM) presented in [11], which quotes the ELM autoencoder (ELM-AE) [20][21][22] as the learning algorithm in each layer. The DELM also has multilayer network structure divided into two parts: the first part uses the ELM-AE to deep learn the original data aiming at obtaining the most representative new data; the second part calculates the network parameters by using the Kernel ELM algorithm with a three-layer structure (the output of the first part, hidden layer, and output layer).…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

A Multiple Hidden Layers Extreme Learning Machine Method and Its Application

Xiao

Mao

2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Extreme learning machine (ELM) is a rapid learning algorithm of the single-hidden-layer feedforward neural network, which randomly initializes the weights between the input layer and the hidden layer and the bias of hidden layer neurons and finally uses the least-squares method to calculate the weights between the hidden layer and the output layer. This paper proposes a multiple hidden layers ELM (MELM for short) which inherits the characteristics of parameters of the first hidden layer. The parameters of the remaining hidden layers are obtained by introducing a method (make the actual output zero error approach the expected hidden layer output). Based on the MELM algorithm, many experiments on regression and classification show that the MELM can achieve the satisfactory results based on average precision and good generalization performance compared to the two-hidden-layer ELM (TELM), the ELM, and some other multilayer ELM.

show abstract

“…Fourthly, target coding (coding for the labels of the samples) is an indispensable part of image classification. With years of research, there are lots of work that have been done on how to extract useful features using ELMs [42,43,44,45], but little work has been done on target coding for ELM. By far, most people adopt one-of-k target coding methods instantly when they use ELM classifiers, while others choose the numeric coding methods to simplify the computation.…”

Section: Objectives and Contributionsmentioning

confidence: 99%

“…Input layer Later, multi-layer ELM [99] and hierarchical ELM [43] were proposed which extend single layer ELM to multiple (hidden) layer networks.…”

Section: Random Connectionsmentioning

confidence: 99%

“…For example, Coates et al [182] analyzed the feature learning ability of single-layer networks and achieved a high performance when the number of hidden nodes and other parameters are pushed to their limits. A method of unsupervised representation learning based on ELM is proposed on in [43], in which, ELM-AE was adopted as the learning unit, and a transferred layer was introduced. Besides, local contrast normalization (LCD) and whitening were employed as pre-processing steps.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced extreme learning machines for image classification

Cui¹

View full text Add to dashboard Cite

First, I would like to thank my supervisor Prof. Huang Guang-Bin for his support and excellent supervision. Thank you for helping me overcome the life and academic obstacles I met these years, and providing help in research thinking and art sense. I will always remember the good advice I have received from you these years. I am also grateful to my co-supervisor Assoc. Prof. Zhang Jie and Assoc. Prof. Lin Zhiping who have given me their kind supervision. Thank you for your time spent on helping me find my way to be a researcher. Great thanks to my project leader, Dr. Yang Yan, who has always been leading me to a young professional researcher when I was in BMW-NTU Future Mobility Lab. She is enthusiastic and always prepared whenever I have questions, and I cannot achieve such works without her help in my first year here. Special thanks to Dr.

show abstract

Hierarchical Extreme Learning Machine for unsupervised representation learning

Cited by 50 publications

References 17 publications

Applications of neural network based methods on stock market prediction: survey

Applications of neural network based methods on stock market prediction: survey

A Multiple Hidden Layers Extreme Learning Machine Method and Its Application

Enhanced extreme learning machines for image classification

Contact Info

Product

Resources

About