1 code implementation • 9 Oct 2022 • Fatih Furkan Yilmaz, Reinhard Heckel
To provide such sets, conformal predictors often estimate a cutoff threshold for the probability estimates based on a calibration set.
1 code implementation • 3 Jun 2022 • Fatih Furkan Yilmaz, Reinhard Heckel
The risk of overparameterized models, in particular deep neural networks, is often double-descent shaped as a function of the model size.
1 code implementation • ICLR 2021 • Reinhard Heckel, Fatih Furkan Yilmaz
Over-parameterized models, such as large deep networks, often exhibit a double descent phenomenon, whereas a function of model size, error first decreases, increases, and decreases at last.
1 code implementation • 20 Oct 2019 • Fatih Furkan Yilmaz, Reinhard Heckel
Image classification problems are typically addressed by first collecting examples with candidate labels, second cleaning the candidate labels manually, and third training a deep neural network on the clean examples.
no code implementations • 25 Sep 2019 • Fatih Furkan Yilmaz, Reinhard Heckel
Classification problems today are typically solved by first collecting examples along with candidate labels, second obtaining clean labels from workers, and third training a large, overparameterized deep neural network on the clean examples.