Results 221 to 230 of about 51,507 (261)

Generative Models in Inorganic Crystals Discovery and Inverse Design

ENERGY &ENVIRONMENTAL MATERIALS, EarlyView.
Generative inverse‐design samples from the vast inorganic crystal design space by starting from target properties such as band gap, stability, and ion transport. This Review examines the representations, generative models, and validation workflows needed to translate candidate structures into stable, potentially synthesizable materials for applications
Tao Li, Xiaolin Liu, Fei Wang, Yan Xiong, Yu Chen, Yan Zhao   +5 more
wiley   +1 more source

A Precision Computational Framework for sLORETA Neurofeedback in Mild Cognitive Impairment: Integration of qEEG Biomarkers and Neuropsychological Metrics. [PDF]

Int J Environ Res Public Health
Dasilva V, Poli D, Pino O.
europepmc   +1 more source

Bayesian-regularized neural network analysis of heat and mass transmission in CMC and water hybrid nanofluid with local thermal non equilibrium conditions. [PDF]

Discov Nano
Hadidi HM, Alhashmi AA, Alkhaldi TM, Farkhad DR, Abbas M, Darem AA.   +5 more
europepmc   +1 more source

Fast efficient coding and sensory adaptation in gain-adaptive recurrent networks. [PDF]

Nat Commun
Prat-Carrabin A, Harl MV, Gershman SJ.
europepmc   +1 more source

Bayesian Uncertainty-aware Deep Learning with noisy labels: Tackling annotation ambiguity in EEG seizure detection. [PDF]

PLoS One
M Shama D, Venkataraman A.
europepmc   +1 more source

Machine learning examination based on Bayesian regularized algorithm for slip effects on solarized Boger nanofluid with activation energy. [PDF]

Discov Nano
Liaqat S, Darem AA, Alghawli ASA, Abbas M, Farkhad DR, Tulu A.   +5 more
europepmc   +1 more source

Compositionality and systematicity emerge from iterated learning in deep linear networks. [PDF]

Proc Natl Acad Sci U S A
Jarvis D, Klein R, Rosman B, Saxe AM.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Bayesian modelling of neural networks

1999
Bayesian methods deal with explicit assumptions and provide rules for reasoning consistently given those assumptions. Bayesian inferences are subjective in the sense that it is not plausible to reason about data without making assumptions. Bayesian NN learning from data features (i) background information used to select a prior probability distribution
Radu Mutihac, Andres Cicuttin, A. Cerdeira Estrada, Alberto A. Colavita   +3 more
openaire   +1 more source