Results 41 to 50 of about 322,666 (307)
A Spectral View of Adversarially Robust Features
CoRR, 2018 Given the apparent difficulty of learning models that are robust to adversarial perturbations, we propose tackling the simpler problem of developing adversarially robust features. Specifically, given a dataset and metric of interest, the goal is to return a function (or multiple functions) that 1) is robust to adversarial perturbations, and 2) has ...
Shivam Garg 0001 +3 more
openaire +3 more sources
Hidden Markov models with spectral features for 2D shape recognition
, 2001 We present a technique using Markov models with spectral features for recognizing 2D shapes. We analyze the properties of Fourier spectral features derived from closed contours of 2D shapes and use these features for 2D pattern recognition.
Cai, Jinhai, Liu, Zhi-Qiang
core +1 more source
Acta Limnologica Brasiliensia, 2017 Aim: In this research, we investigated the spectral variability of the specific phytoplankton absorption coefficient, a*φ, measured in a tropical meso-to-hypertrophic reservoir, aiming to find spectral features associated with the chlorophyll-a (chla ...
Fernanda Sayuri Yoshino Watanabe +5 more
doaj +1 more source
Combined Method for Informative Feature Selection for Speech Pathology Detection
Доклады Белорусского государственного университета информатики и радиоэлектроники, 2023 The task of detecting vocal abnormalities is characterized by a small amount of available data for training, as a consequence of which classification systems that use low-dimensional data are the most relevant.
D. S. Likhachov +3 more
doaj +1 more source
DiSC: Differential Spectral Clustering of Features
Advances in Neural Information Processing Systems 35, 2022 Selecting subsets of features that differentiate between two conditions is a key task in a broad range of scientific domains. In many applications, the features of interest form clusters with similar effects on the data at hand. To recover such clusters we develop DiSC, a data-driven approach for detecting groups of features that differentiate between ...
Ram Dyuthi Sristi +2 more
openaire +3 more sources
High resolution observations of spectral width features associated with ULF wave signatures in artificial HF radar backscatter [PDF]
, 2004 International audienceThe EISCAT high power heating facility at Tromsø, northern Norway, has been utilised to generate artificial radar backscatter in the fields of view of the CUTLASS HF radars.
Woodfield, E.E. +30 more
core +1 more source
Pediatric Blood &Cancer, EarlyView.ABSTRACT Background PIK3CA‐related overgrowth spectrum (PROS) includes several rare overgrowth disorders resulting from somatic gain‐of‐function mutations in PIK3CA. Despite treatment advances, including the recent approval of alpelisib for PROS in the United States, literature detailing the patient experience with PROS is limited.
Vamsi Bollu +8 more
wiley +1 more source
Musical instrument classification using non-negative matrix factorization algorithms [PDF]
, 2006 14.08.13 KB. Ok to add accepted version to Spiral. IEEEIn this paper, a class of algorithms for automatic classification of individual musical instrument sounds is presented.
Benetos, Emmanouil +5 more
core +1 more source
Conventional to Deep Ensemble Methods for Hyperspectral Image Classification: A Comprehensive Survey
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingHyperspectral image classification (HSIC) has become a hot research topic. Hyperspectral imaging (HSI) has been widely used in a wide range of real-world application areas due to the in-depth spectral information stored within each pixel. Noticeably, the
Farhan Ullah +5 more
doaj +1 more source
Open Geosciences, 2017 Surfaces weathering of rocks in which mineral materials may be similar to or quite different from the minerals in the underlying parent rock completely control the reflectance spectra of the terrain.
Zhou Ke-Fa, Wang Shan-Shan
doaj +1 more source