Results 21 to 30 of about 927 (160)
Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networks. [PDF]
Entropy (Basel), 2021 We make three related contributions motivated by the challenge of training stochastic neural networks, particularly in a PAC-Bayesian setting: (1) we show how averaging over an ensemble of stochastic neural networks enables a new class of \emph{partially-
Biggs F, Guedj B.
europepmc +9 more sources
EnergiesUnder the dual carbon objectives, wind power penetration has accelerated markedly. However, the inherent volatility and insufficient peak regulation capability in energy storage allocation hamper efficient grid integration.
Kai Qi +4 more
doaj +2 more sources
Shock and VibrationThe current methods for early fault diagnosis of rolling bearing have some flaws, such as poor fault feature information and insufficient fault feature extraction capability, which makes it challenging to guarantee fault diagnosis accuracy.
Wei Yuan +5 more
doaj +2 more sources
Research on active compounds regarding SGMD for the treatment of COVID-19 based on network pharmacology and molecular docking [PDF]
, 2020 Abstract Background: Retrieve Curative effect of Six Gentlemen Modified Decoction (SGMD) in treating with coronavirus disease ( COVID-19 ) by network pharmacology and verify its authenticity by molecular docking. Methods: The chemical constituents, effective components, and action targets were screened using TCMSP. COVID-19 related targets were
Donglai M +5 more
europepmc +2 more sources
MXene Membrane as Multifunctional Interface for Vapor Splitting via Photothermal-Catalytic Membrane Distillation. [PDF]
Adv MaterA multifunctional MXene‐based membrane integrates photothermal evaporation and photocatalytic vapor splitting in a sweeping‐gas membrane distillation (PTC‐SGMD) platform, simultaneously generating freshwater and hydrogen. The SrTiO3/MX@PVDF interface leverages broad‐spectrum solar absorption, efficient heat/mass transfer, and gas–solid catalysis to ...
Sun J +11 more
europepmc +2 more sources
Conformer-RL: A deep reinforcement learning library for conformer generation. [PDF]
J Comput Chem, 2022 Conformer‐RL is an open‐source Python package for generating conformers of molecules and polymers using deep reinforcement learning. The package includes pretrained models for generating conformers of several classes of covalently bonded molecules as well as a robust library for training and evaluating tailored models for custom molecules and tasks ...
Jiang R +5 more
europepmc +2 more sources
SGMD: the Soybean Genomics and Microarray Database [PDF]
Nucleic Acids Research, 2004 The Soybean Genomics and Microarray Database (SGMD) attempts to provide an integrated view of the interaction of soybean with the soybean cyst nematode and contains genomic, EST and microarray data with embedded analytical tools allowing correlation of soybean ESTs with their gene expression profiles.
Nadim W, Alkharouf, Benjamin F, Matthews
openaire +2 more sources
Journal of Marine Science and Engineering, 2023 The marine controlled-source electromagnetic (CSEM) method is an efficient tool for hydrocarbon exploration. The amplitudes of signals decay rapidly with the increasing offset, so signals are easily contaminated by various kinds of noise.
Yijie Chen, Zhenwei Guo, Dawei Gao
doaj +1 more source
Case Studies in Thermal Engineering, 2021 The enhancement of distillate water obtained from sweeping gas membrane distillation (SGMD) is rarely discussed in published works compared with other membrane distillation (MD) configurations, although it has the lowest thermal losses and does not need ...
Mahmoud Badawy Elsheniti +4 more
doaj +1 more source
IEEE Access, 2023 It is always a hot and challenging problem to extract the characteristic information of roller bearings from strong noise interference. Conventional Hilbert-Huang Transform (HHT), Local Mean Decomposition (LMD), Local Feature-Scale Decomposition (LCD ...
Yanfei Liu +5 more
doaj +1 more source