Fast decorrelated neural network ensembles with random weights

194 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Forest Floor Visualizations of Random Forests (2016, background): “Such functions as Friedman#1 and ’Mexican hat’ are known examples [1].”
Distributed learning for Random Vector Functional-Link networks (2015, methodology): “Each image is composed of exactly 32 32 pixels, and each pixel is further represented by 3 integer values in the interval [1,255], one for each color channel in the RGB color space.”
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning (2020, background): “For instance, here Z = ∑ p∈Pv(X) zp can be a uniform distribution over [1, 2].”
Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks (2015, methodology): “Other work has explicitly trained decorrelated ensembles of neural networks by penalizing positive correlation between error distributions [2,23,29].”
Ensemble Classification and Regression-Recent Developments, Applications and Future Directions [Review Article] (2016, background): “larization can be found in [107], where all”
A survey of randomized algorithms for training neural networks (2016, methodology): “In [2], the author trains a pool of decorrelated RVFL within the negative correlation learning framework to obtain an ensemble classifier.”
A comprehensive evaluation of random vector functional link networks (2016, methodology): “In [1], decorrelated RVFL ensemble was introduced based on the negative correlation learning.”