منابع مشابه
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
Deep Neural Networks (DNNs) have recently been shown to be vulnerable against adversarial examples, which are carefully crafted instances that can mislead DNNs to make errors during prediction. To better understand such attacks, a characterization is needed of the properties of regions (the so-called ‘adversarial subspaces’) in which adversarial examples lie. We tackle this challenge by charact...
متن کاملThe Intrinsic Dimensionality of Spectro-polarimetric Data
The amount of information available in spectro-polarimetric data is estimated. To this end, the intrinsic dimensionality of the data is inferred with the aid of a recently derived estimator based on nearest-neighbor considerations and obtained applying the principle of maximum likelihood. We show in detail that the estimator correctly captures the intrinsic dimension of artificial datasets with...
متن کاملEstimating the intrinsic dimensionality of hyperspectral images
Estimating the intrinsic dimensionality (ID) of an intrinsically low (d-) dimensional data set embedded in a high (n-) dimensional input space by conventional Principal Component Analysis (PCA) is computationally hard because PCA scales cubic (O(n)) with the input dimension [11]. Besides this computational drawback, global PCA will overestimate the ID if the data manifold is curved. In this pap...
متن کاملIntrinsic Dimensionality Estimation in Visualizing Toxicity Data
Over the years, a number of dimensionality reduction techniques have been proposed and used in chemo informatics to perform nonlinear mappings. Nevertheless, data visualization techniques can be efficiently applied for dimensionality reduction mainly in a case if the data are not really high-dimensional and can be represented as a nonlinear low-dimensional manifold when it is possible to reduce...
متن کاملLocal Intrinsic Dimensionality Based Features for Clustering
One of the fundamental tasks of unsupervised learning is dataset clustering, to partition the input dataset into clusters composed by somehow “similar” objects that “differ” from the objects belonging to other classes. To this end, in this paper we assume that the different clusters are drawn from different, possibly intersecting, geometrical structures represented by manifolds embedded into a ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: SIGSPATIAL Special
سال: 2010
ISSN: 1946-7729,1946-7729
DOI: 10.1145/1862413.1862416