scholarly journals Comparative Study on Subject Classification of Academic Videos Using Noisy Transcripts

2010 ◽  
Author(s):  
Hau-Wen Chang ◽  
Hung-sik Kim ◽  
Shuyang Li ◽  
Jeongkyu Lee ◽  
Dongwon Lee
Keyword(s):  
Comparative Study ◽  
Subject Classification

scholarly journals CNN architecture comparison for radio galaxy classification

2021 ◽  
Vol 503 (2) ◽  
pp. 1828-1846
Author(s):  
Burger Becker ◽  
Mattia Vaccari ◽  
Matthew Prescott ◽  
Trienko Grobler
Keyword(s):  
Comparative Study ◽  
Galaxy Evolution ◽  
Radio Galaxy ◽  
Recognition Performance ◽  
Model Complexity ◽  
Great Promise ◽  
Radio Sources ◽  
Morphological Classification ◽  
Computational Performance

ABSTRACT The morphological classification of radio sources is important to gain a full understanding of galaxy evolution processes and their relation with local environmental properties. Furthermore, the complex nature of the problem, its appeal for citizen scientists, and the large data rates generated by existing and upcoming radio telescopes combine to make the morphological classification of radio sources an ideal test case for the application of machine learning techniques. One approach that has shown great promise recently is convolutional neural networks (CNNs). Literature, however, lacks two major things when it comes to CNNs and radio galaxy morphological classification. First, a proper analysis of whether overfitting occurs when training CNNs to perform radio galaxy morphological classification using a small curated training set is needed. Secondly, a good comparative study regarding the practical applicability of the CNN architectures in literature is required. Both of these shortcomings are addressed in this paper. Multiple performance metrics are used for the latter comparative study, such as inference time, model complexity, computational complexity, and mean per class accuracy. As part of this study, we also investigate the effect that receptive field, stride length, and coverage have on recognition performance. For the sake of completeness, we also investigate the recognition performance gains that we can obtain by employing classification ensembles. A ranking system based upon recognition and computational performance is proposed. MCRGNet, Radio Galaxy Zoo, and ConvXpress (novel classifier) are the architectures that best balance computational requirements with recognition performance.

Structure and Semantics of Tactile Verbs in a Comparative Aspect (On the Material of the English, German and Russian Languages)

2021 ◽  
pp. 58-63
Author(s):  
Yu. A. Sakhno
Keyword(s):  
Comparative Study ◽  
Semantic Features ◽  
Semantic Classification ◽  
Comparative Aspect ◽  
Similarities And Differences ◽  
The Comparative Study ◽  
Linguistic Units

This article deals with the study of the structural and semantic features of tactile verbs (hereinafter TVs) in English, German and Russian. Particular attention is paid to the comparative study of TVs, which allows us to identify structural and semantic similarities and differences of linguistic units studied. The structural and semantic classification of TVs in the compared languages is also provided.

scholarly journals ON THE CLASSIFICATION OF NUCLEAR C*-ALGEBRAS

2002 ◽  
Vol 85 (1) ◽  
pp. 168-210 ◽  
Author(s):  
MARIUS DADARLAT ◽  
SØREN EILERS
Keyword(s):  
Subject Classification ◽  
Unified Approach ◽  
C Algebras ◽  
Starting Point ◽  
K Theory

We employ results from KK-theory, along with quasidiagonality techniques, to obtain wide-ranging classification results for nuclear C*-algebras. Using a new realization of the Cuntz picture of the Kasparov groups we show that two morphisms inducing equal KK-elements are approximately stably unitarily equivalent. Using K-theory with coefficients to associate a partial KK-element to an approximate morphism, our result is generalized to cover such maps. Conversely, we study the problem of lifting a (positive) partial KK-element to an approximate morphism. These results are employed to obtain classification results for certain classes of quasidiagonal C*-algebras introduced by H. Lin, and to reprove the classification of purely infinite simple nuclear C*-algebras of Kirchberg and Phillips. It is our hope that this work can be the starting point of a unified approach to the classification of nuclear C*-algebras.2000 Mathematical Subject Classification: primary 46L35; secondary 19K14, 19K35, 46L80.

Intra-subject classification of gait phases by neural network interpretation of EMG signals

2019 ◽  
Vol 74 ◽  
pp. 13-14
Author(s):  
F. Di Nardo ◽  
C. Morbidoni ◽  
A. Strazza ◽  
G. Mascia ◽  
F. Verdini ◽  
...  
Keyword(s):  
Neural Network ◽  
Subject Classification
Sign in / Sign up

Export Citation Format

Share Document