A modified Lanczos Algorithm for fast regularization of extreme learning machines
Copyright policy )A modified Lanczos Algorithm for fast regularization of extreme learning machines
Abstract This paper presents a new regularization for Extreme Learning Machines (ELMs). ELMs are Randomized Neural Networks (RNNs) that are known for their fast training speed and good accuracy. Nevertheless the complexity of ELMs has to be selected, and regularization has to be performed in order to avoid underfitting or overfitting. Therefore, a novel Regularization is proposed using a modified Lanczos Algorithm: Iterative Lanczos Extreme Learning Machine (Lan-ELM). As summarized in the experimental Section, the computational time is on average divided by 4 and the Normalized MSE is on average reduced by 11%. In addition, the proposed method can be intuitively parallelized, which makes it a very valuable tool to analyze huge data sets in real-time.
- University of Iowa United States
- University of Helsinki Finland
- Arcada University of Applied Sciences Finland
- University of Houston United States
- Hanken School of Economics Finland
ta113, 1 - Self archived, neural networks (information technology), neuronnät, Extreme learning machines, 1- Publicerad utomlands, 113 Computer and information sciences, Classification, 0- Ingen affiliation med ett företag, algorithms, 1- Minst en av författarna har en utländsk affiliation, Regression, KOTA2020, machine learning, http://hdl.handle.net/10227/511074, maskininlärning, Regularization, PREM2020_10, 0 - Not open access, algoritmer, Lanczos algorithm, Neural networks
ta113, 1 - Self archived, neural networks (information technology), neuronnät, Extreme learning machines, 1- Publicerad utomlands, 113 Computer and information sciences, Classification, 0- Ingen affiliation med ett företag, algorithms, 1- Minst en av författarna har en utländsk affiliation, Regression, KOTA2020, machine learning, http://hdl.handle.net/10227/511074, maskininlärning, Regularization, PREM2020_10, 0 - Not open access, algoritmer, Lanczos algorithm, Neural networks
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).17 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Top 10% influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Top 10% impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Top 10%
Citations provided by BIP!Popularity provided by BIP!