3 papers
cs.CV2022
Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation
Wei Dai, Daniel Berleant
Accuracies of deep learning (DL) classifiers are often unstable in that they may change significantly when retested on adversarial images, imperfect images, or perturbed images. Th…
q-fin.GN2021
Moore's law, Wright's law and the Countdown to Exponential Space
Daniel Berleant, Venkat Kodali, Richard Segall +2
Technologies have often been observed to improve exponentially over time. In practice this often means identifying a constant known as the doubling time, describing the time period…
math.ST2004
Direct pivotal predictive inference
George Kahrimanis, Daniel Berleant
Without assuming any pdf for some measured parameter, we derive a predictive pdf for the outcome of a second measurement, given the outcome of the first measurement and two common…