Results 31 to 40 of about 6,466,948 (249)

A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

open access: yesCoRR, 2023
Bayesian optimization is a highly efficient approach to optimizing objective functions which are expensive to query. These objectives are typically represented by Gaussian process (GP) surrogate models which are easy to optimize and support exact inference.
Yucen Lily Li   +2 more
openaire   +4 more sources

Bayesian Recurrent Neural Networks

open access: yesCoRR, 2017
In this work we explore a straightforward variational Bayes scheme for Recurrent Neural Networks. Firstly, we show that a simple adaptation of truncated backpropagation through time can yield good quality uncertainty estimates and superior regularisation at only a small extra computational cost during training, also reducing the amount of parameters by
Meire Fortunato   +2 more
openaire   +3 more sources

Function Space Bayesian Pseudocoreset for Bayesian Neural Networks

open access: yesAdvances in Neural Information Processing Systems 36, 2023
A Bayesian pseudocoreset is a compact synthetic dataset summarizing essential information of a large-scale dataset and thus can be used as a proxy dataset for scalable Bayesian inference. Typically, a Bayesian pseudocoreset is constructed by minimizing a divergence measure between the posterior conditioning on the pseudocoreset and the posterior ...
Balhae Kim, Hyungi Lee, Juho Lee 0001
openaire   +4 more sources

All-Spin Bayesian Neural Networks [PDF]

open access: yesIEEE Transactions on Electron Devices, 2020
Probabilistic machine learning enabled by the Bayesian formulation has recently gained significant attention in the domain of automated reasoning and decision-making. While impressive strides have been made recently to scale up the performance of deep Bayesian neural networks, they have been primarily standalone software efforts without any regard to ...
Kezhou Yang   +3 more
openaire   +3 more sources

Applying Bayesian Regularization for Acceleration of Levenberg-Marquardt based Neural Network Training

open access: yesInternational Journal of Interactive Multimedia and Artificial Intelligence, 2018
Neural network is widely used for image classification problems, and is proven to be effective with high successful rate. However one of its main challenges is the significant amount of time it takes to train the network.
Azizah Suliman, Batyrkhan Omarov
doaj   +1 more source

Bayesian and information-theoretic tools for neuroscience [PDF]

open access: yes, 2007
The overarching purpose of the studies presented in this report is the exploration of the uses of information theory and Bayesian inference applied to neural codes. Two approaches were taken: Starting from first principles, a coding mechanism is proposed,
Endres, Dominik M.
core   +2 more sources

Using topological data analysis for building Bayesan neural networks

open access: yesНаучно-технический вестник информационных технологий, механики и оптики
For the first time, a simplified approach to constructing Bayesian neural networks is proposed, combining computational efficiency with the ability to analyze the learning process.
A. S. Vatian   +4 more
doaj   +1 more source

Investigating Performance of Bayesian and Levenberg-Marquardt Neural Network in Comparison Classical Models in Stock Price Forecasting [PDF]

open access: yesتحقیقات مالی, 2017
Accurate forecasting of stock prices according to high volatility and inherent risk of stock market is a major concern of investors and financial analysts, hence applying novel approaches to predict the stock priceisan inevitable necessity.
Hossein Fakhari   +2 more
doaj   +1 more source

Neural-Network Heuristics for Adaptive Bayesian Quantum Estimation - Source Code and Data

open access: yes, 2020
Source code and data for paper " Neural-Network Heuristics for Adaptive Bayesian Quantum Estimation", seehttps://arxiv.org/abs/2003.02183For more information about the source code read "README.md".
Daniel Braun (7299476)   +2 more
core   +1 more source

Bayesian Neural Network Priors Revisited

open access: yesCoRR, 2021
Isotropic Gaussian priors are the de facto standard for modern Bayesian neural network inference. However, it is unclear whether these priors accurately reflect our true beliefs about the weight distributions or give optimal performance. To find better priors, we study summary statistics of neural network weights in networks trained using stochastic ...
Vincent Fortuin   +7 more
openaire   +4 more sources

Home - About - Disclaimer - Privacy