Results 41 to 50 of about 234,090 (282)
A program for the Bayesian Neural Network in the ROOT framework
, 2011 We present a Bayesian Neural Network algorithm implemented in the TMVA package, within the ROOT framework. Comparing to the conventional utilization of Neural Network as discriminator, this new implementation has more advantages as a non-parametric ...
Brun +11 more
core +1 more source
Scaling Up Bayesian Neural Networks with Neural Networks
, 2023 25 ...
Moslemi, Zahra +3 more
openaire +2 more sources
Weight Priors for Learning Identity Relations [PDF]
, 2019 Learning abstract and systematic relations has been an open issue in neural network learning for over 30 years. It has been shown recently that neural networks do not learn relations based on identity and are unable to generalize well to unseen data. The
Kopparti, R. M., Weyde, T.
core
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Background Poststroke fatigue (PSF) and frailty share substantial overlap in their manifestations, yet previous research has yielded conflicting results due to the use of heterogeneous frailty assessment tools. Objective To evaluate the independent impact of frailty on PSF using a unified measurement system (Tilburg Frailty Indicator, TFI ...
Chuan‐Bang Chen +6 more
wiley +1 more source
Prediction of concrete fatigue durability using Bayesian neural networks
Computer Assisted Methods in Engineering and Science, 2022 The utility of Bayesian neural networks to predict concrete fatigue durability as a function of concrete mechanical parameters of a specimen and characteristics of the loading cycle is investigated.
Marek Słoński
doaj
Representing Uncertainty in Property Valuation Through a Bayesian Deep Learning Approach
Real Estate Management and Valuation, 2020 Although deep learning-based valuation models are spreading throughout the real estate industry following the artificial intelligence boom, property owners and investors continue to doubt the accuracy of the results.
Lee Changro, Park Keith Key-Ho
doaj +1 more source
Bayesian continual learning via spiking neural networks
Frontiers in Computational Neuroscience, 2022 Among the main features of biological intelligence are energy efficiency, capacity for continual adaptation, and risk management via uncertainty quantification. Neuromorphic engineering has been thus far mostly driven by the goal of implementing energy-efficient machines that take inspiration from the time-based computing paradigm of biological brains.
Skatchkovsky, Nicolas +2 more
openaire +5 more sources
Integrative Approaches for DNA Sequence‐Controlled Functional Materials
Advanced Functional Materials, EarlyView.DNA is emerging as a programmable building block for functional materials with applications in biomimicry, biochemical, and mechanical information processing. The integration of simulations, experiments, and machine learning is explored as a means to bridge DNA sequences with macroscopic material properties, highlighting current advances and providing ...
Aaron Gadzekpo +4 more
wiley +1 more source
Journal of the Brazilian Computer Society, 1997 Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a solution to the problem of ...
openaire +3 more sources
Advanced Functional Materials, EarlyView.This study establishes a materials‐driven framework for entropy generation within standard CMOS technology. By electrically rebalancing gate‐oxide traps and Si‐channel defects in foundry‐fabricated FDSOI transistors, the work realizes in‐materia control of temporal correlation – achieving task adaptive entropy optimization for reinforcement learning ...
Been Kwak +14 more
wiley +1 more source