Universal adversarial perturbations
in today’s paper Moosavi-Dezfooli et al., show us how to create a _single_ perturbation that causes the vast majority of input images to be misclassified.
(tags: adversarial-classification spam image-recognition ml machine-learning dnns neural-networks images classification perturbation papers)
“Use trees. Not too deep. Mostly ensembles.”
snarky summary of ‘Data-driven Advice for Applying Machine Learning to Bioinformatics Problems’, a recent analysis paper of ML algorithms
(tags: algorithms machine-learning bioinformatics funny advice classification)