Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Trans. Neural Networks 17(4) (2006) 879–892] has recently proposed an incremental extreme learning machine (I-ELM), which randomly adds hidden nodes incrementally and analytically determines the output weights. Although hidden nodes are generated randomly, the network constru...

Extreme learning machine (ELM) as an emergent technology has shown its good performance in classification applications. However, ELM algorithm needs to find the inversion of matrix in nature, which will limit its application on many occasions. This paper proposes an ELM speedup algorithm based on the analysis of ELM algorithm. By applying randomized approximation method, the proposed algorithm ...

Roswell Park Cancer Institute, Department of Molecular and Cellular Biology, Elm and Carlton Streets, Buffalo, New York 14263-0001, U.S.A., Roswell Park Cancer Institute, Department of Human Genetics, Elm and Carlton Streets, Buffalo, New York 1^263-0001, U.S.A., Roswell Park Cancer Institute, Division of Medicine, Elm and Carlton Streets, Buffalo, New York 14263-0001, U.S.A., and Ludwig Instit...

Extreme Learning Machine (ELM) is popular in batch learning, sequential and progressive due to its speed, easy integration, generalization ability. While, Traditional ELM cannot train massive data rapidly efficiently memory residence, high time space complexity. In ELM, the hidden layer typically necessitates a huge number of nodes. Furthermore, there no certainty that arrangement weights biase...

In the present study, we investigated the effects of chronic exposure (14 and 28 days) to a 0.5 mT 50 Hz extremely low-frequency magnetic field (ELM) on the dendritic spine density and shape in the superficial layers of the medial entorhinal cortex (MEC). We performed Golgi staining to reveal the dendritic spines of the principal neurons in rats. The results showed that ELM exposure induced a d...

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme l...