Results 11 to 20 of about 617,748 (267)
Compressing Fisher Vector for Robust Face Recognition
IEEE Access, 2017 One major topic for robust face recognition could be the efficient encoding of facial descriptors. Among various encoders, Fisher vector (FV) is one of the probabilistic methods that yield promising results.
Hongjun Wang, Jiani Hu, Weihong Deng
doaj +1 more source
Emergence of time persistence in a data-driven neural network model
eLife, 2023 Establishing accurate as well as interpretable models of network activity is an open challenge in systems neuroscience. Here, we infer an energy-based model of the anterior rhombencephalic turning region (ARTR), a circuit that controls zebrafish swimming
Sebastien Wolf +4 more
doaj +1 more source
Energies, 2020 Thickness of tectonically deformed coal (TDC) has positive correlations with the susceptible gas outbursts in coal mines. To predict the TDC thickness of the coalbed, we proposed a prediction method using seismic attributes based on the deep belief ...
Xin Wang, Tongjun Chen, Hui Xu
doaj +1 more source
IEEE Open Journal of Instrumentation and Measurement, 2022 Deep learning neural network serves as a powerful tool for visual anomaly detection (AD) and fault diagnosis, attributed to its strong abstractive interpretation ability in the representation domain.
Jie Lin, Song Chen, Enping Lin, Yu Yang
doaj +1 more source
Investigation of Metastable Low Dimensional Halometallates
Molecules, 2022 The solvothermal synthesis, structure determination and optical characterization of five new metastable halometallate compounds, [1,10-phenH][Pb3.5I8] (1), [1,10-phenH2][Pb5I12]·(H2O) (2), [1,10-phen][Pb2I4] (3), [1,10-phen]2[Pb5Br10] (4) and [1,10-phenH]
Navindra Keerthisinghe +6 more
doaj +1 more source
SAELGMDA: Identifying human microbe–disease associations based on sparse autoencoder and LightGBM
Frontiers in Microbiology, 2023 IntroductionIdentification of complex associations between diseases and microbes is important to understand the pathogenesis of diseases and design therapeutic strategies.
Feixiang Wang +5 more
doaj +1 more source
Binary Codes Based on Non-Negative Matrix Factorization for Clustering and Retrieval
IEEE Access, 2020 Traditional non-negative matrix factorization methods cannot learn the subspace from the high-dimensional data space composed of binary codes. One hopes to discover a compact parts-based representation composed of binary codes, which can uncover the ...
Jiang Xiong +3 more
doaj +1 more source
Mixing Autoencoder With Classifier: Conceptual Data Visualization
IEEE Access, 2020 In this paper, a neural network that is able to form a low-dimensional topological hidden representation is explained. The neural network can be trained as an autoencoder, as a classifier or as a mixture of both and produces a different low-dimensional ...
Pitoyo Hartono
doaj +1 more source
Frontiers in Systems BiologyIntroductionThe availability of large-scale multi-omic data has revolution-ized the study of cellular machinery, enabling a systematic understanding of biological processes.
Andrea Angarita-Rodríguez +10 more
doaj +1 more source
A GALERKIN APPROXIMATION METHOD INCLUDING SPACE DIMENSIONAL REDUCTION - APPLIED FOR SOLUTION OF A HEAT CONDUCTION EQUATION [PDF]
Applied Computer Science, 2012 A multivariate data fitting procedure, based on the Galerkin minimization method, is studied in this paper. The main idea of the developed approach consists in projecting the set of data points from the original, higherdimensional space, onto a line ...
Krzysztof NAKONIECZNY
doaj