A modified Lanczos Algorithm for fast regularization of extreme learning machines

Renjie Hu*, Edward Ratner, David Stewart, Kaj Mikael Björk, Amaury Lendasse

*Motsvarande författare för detta arbete

Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

Sammanfattning

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.

OriginalspråkEngelska
Referentgranskad vetenskaplig tidskriftNeurocomputing
Volym414
Sidor (från-till)172-181
Antal sidor10
ISSN0925-2312
DOI
StatusPublicerad - 14.07.2020
MoE-publikationstypA1 Originalartikel i en vetenskaplig tidskrift

Nyckelord

  • 113 Data- och informationsvetenskap

Fingeravtryck Fördjupa i forskningsämnen för ”A modified Lanczos Algorithm for fast regularization of extreme learning machines”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här