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 ...
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 ...
GitHub

tutorial_tensorflow_real-time_simultaneous_classifiers.ipynb

"For this demo, we will use four of our transfer learning classifiers: `danceability`, `voice_instrumental`, `mood_aggressive`, and `mood_happy`. These and more ...