ELM surrogates can replace gradient-trained deep networks for low-dimensional sequential radiative transfer emulation with far less training time and data, while the image mapping task needs a 50-model ensemble that gains training speed but loses inference speed.
Regularized Extreme Learning Machine , 2009 IEEE Symposium on Computational Intelligence and Data Mining\/ , pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.EP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Extreme Learning Machines for Exoplanet Simulations: A Faster, Lightweight Alternative to Deep Learning
ELM surrogates can replace gradient-trained deep networks for low-dimensional sequential radiative transfer emulation with far less training time and data, while the image mapping task needs a 50-model ensemble that gains training speed but loses inference speed.