Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Diochnos, Dimitrios I."'
Deep neural models have achieved state of the art performance on a wide range of problems in computer science, especially in computer vision. However, deep neural networks often require large datasets of labeled samples to generalize effectively, and
Externí odkaz:
http://arxiv.org/abs/2408.07221
In many practical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers have recei
Externí odkaz:
http://arxiv.org/abs/2311.18083
In this work, we initiate a formal study of probably approximately correct (PAC) learning under evasion attacks, where the adversary's goal is to \emph{misclassify} the adversarially perturbed sample point $\widetilde{x}$, i.e., $h(\widetilde{x})\neq
Externí odkaz:
http://arxiv.org/abs/1906.05815
We study adversarial perturbations when the instances are uniformly distributed over $\{0,1\}^n$. We study both "inherent" bounds that apply to any problem and any classifier for such a problem as well as bounds that apply to specific problems and sp
Externí odkaz:
http://arxiv.org/abs/1810.12272
Many modern machine learning classifiers are shown to be vulnerable to adversarial perturbations of the instances. Despite a massive amount of work focusing on making classifiers robust, the task seems quite challenging. In this work, through a theor
Externí odkaz:
http://arxiv.org/abs/1809.03063
Recently, Mahloujifar and Mahmoody (TCC'17) studied attacks against learning algorithms using a special case of Valiant's malicious noise, called $p$-tampering, in which the adversary gets to change any training example with independent probability $
Externí odkaz:
http://arxiv.org/abs/1711.03707
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Diochnos, Dimitrios I.
In this report a computational study of ConceptNet 4 is performed using tools from the field of network analysis. Part I describes the process of extracting the data from the SQL database that is available online, as well as how the closure of the in
Externí odkaz:
http://arxiv.org/abs/1304.5863
Publikováno v:
J. Symb. Comput. 44(7): 818-835 (2009)
This paper is concerned with exact real solving of well-constrained, bivariate polynomial systems. The main problem is to isolate all common real roots in rational rectangles, and to determine their intersection multiplicities. We present three algor
Externí odkaz:
http://arxiv.org/abs/1203.1017