Robust neural learning from unbalanced data samples

By Yi Lu, Hong Guo, Lee A. Feldkamp. 1998

How researchers see this paper

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

Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure (2019, methodology): “For example, duplicating instances of the minority class as in (Lu, Guo, and Feldkamp 1998) has been used as pre-processing steps for mitigating class imbalance, yet is not capable of running adaptively during training itself.”
Adaptive boosting for SAR automatic target recognition (2007, background): “It is a standard practice to alleviate this problem by augmenting minority classes with sample duplicates [24, 25], so that all classes are equally populated, which improves the accuracy of the outlined training of RBF.”
A supervised learning approach for imbalanced data sets (2008, background): “00 ©2008 IEEE ods such as over-sampling and under-sampling [7, 14] modify the prior probability of the majority and minority class in the training set to obtain a more balanced number of instances in each class.”