Kernel-Based Multilayer Extreme Learning Machines for Representation Learning

Recently, multilayer extreme learning machine (ML-ELM) was applied to stacked autoencoder (SAE) for representation learning. In contrast to traditional SAE, the training time of ML-ELM is significantly reduced from hours to seconds with high accuracy. However, ML-ELM suffers from several drawbacks:...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transaction on neural networks and learning systems Ročník 29; číslo 3; s. 757 - 762
Hlavní autoři:	Wong, Chi Man, Vong, Chi Man, Wong, Pak Kin, Cao, Jiuwen
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.03.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Benchmark testing Benchmarks Datasets Kernel Kernel learning Learning Learning algorithms Learning systems Manuals multilayer extreme learning machine (ML-ELM) Neural networks Nonhomogeneous media Reconstruction representation learning Representations stacked autoencoder (SAE) Training Tuning
ISSN:	2162-237X, 2162-2388
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!