Zobrazeno 1 - 10
of 170
pro vyhledávání: '"Hosseini, Mehran"'
Conformal Prediction (CP) is a popular uncertainty quantification method that provides distribution-free, statistically valid prediction sets, assuming that training and test data are exchangeable. In such a case, CP's prediction sets are guaranteed
Externí odkaz:
http://arxiv.org/abs/2405.18942
Autor:
Hosseini, Mehran, Hosseini, Peyman
Scaled Dot Product Attention (SDPA) is the backbone of many modern deep-learning models. It is so versatile that it has been used in natural language, vision, and multi-modal domains with very little change compared to its original formulation. This
Externí odkaz:
http://arxiv.org/abs/2403.01643
We introduce two algorithms for computing tight guarantees on the probabilistic robustness of Bayesian Neural Networks (BNNs). Computing robustness guarantees for BNNs is a significantly more challenging task than verifying the robustness of standard
Externí odkaz:
http://arxiv.org/abs/2401.11627
Autor:
Hosseini, Mehran, Hosseini, Peyman
The enduring inability of image generative models to recreate intricate geometric features, such as those present in human hands and fingers has been an ongoing problem in image generation for nearly a decade. While strides have been made by increasi
Externí odkaz:
http://arxiv.org/abs/2401.01951
Autor:
Hosseini, Peyman, Hosseini, Mehran, Al-Azzawi, Sana Sabah, Liwicki, Marcus, Castro, Ignacio, Purver, Matthew
We study the influence of different activation functions in the output layer of deep neural network models for soft and hard label prediction in the learning with disagreement task. In this task, the goal is to quantify the amount of disagreement via
Externí odkaz:
http://arxiv.org/abs/2303.02468
We consider the problem of deciding termination of single-path while loops with integer variables, affine updates, and affine guard conditions. The question is whether such a loop terminates on all integer initial values. This problem is known to be
Externí odkaz:
http://arxiv.org/abs/1902.07465
We study the growth behaviour of rational linear recurrence sequences. We show that for low-order sequences, divergence is decidable in polynomial time. We also exhibit a polynomial-time algorithm which takes as input a divergent rational linear recu
Externí odkaz:
http://arxiv.org/abs/1806.07740
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We give explicit formulas for the number of distinct elliptic curves over a finite field, up to isomorphism, in two families of curves introduced by C.~Doche, T.~Icart and D.~R. Kohel.
Externí odkaz:
http://arxiv.org/abs/1510.01849
Autor:
Dorranipour, Davood, Pourjafari, Fahimeh, Malekpour-Afshar, Reza, Basiri, Mohsen, Hosseini, Mehran
Publikováno v:
Naunyn-Schmiedeberg's Archives of Pharmacology; May2024, Vol. 397 Issue 5, p2971-2985, 15p