IEEE

Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation

Abstract: Deep learning (DL) classifiers are often unstable in that they may change significantly when retested on perturbed images or low quality images. This paper adds to the fundamental body of ...
IEEE

Learning classifiers without negative examples: A reduction approach

Abstract: The problem of PU Learning, i.e., learning classifiers with positive and unlabelled examples (but not negative examples), is very important in information retrieval and data mining. We ...
Microsoft

Denoised smoothing: Provably defending pretrained classifiers against adversarial examples

Editor’s note: This post and its research are the result of the collaborative efforts of a team of researchers comprising former Microsoft Research Engineer Hadi Salman (opens in new tab), CMU PhD ...
GitHub

evaluateClassifiers_examples.rst

In the PyRBP, we integrate several machine learning classifiers from sklearn and implement several classical deep learning models for users to perform performance tests, for which we provide two ...
POWER Magazine

Dynamic classifiers improve pulverizer performance and more

No one in this industry underestimates the difficulty of transforming an unwieldy and distinctly nonuniform substance like coal into a fuel whose physical and chemical characteristics are consistent ...