Results 41 to 50 of about 3,905,952 (289)
Non-homogeneous dynamic Bayesian networks for continuous data [PDF]
, 2011 : Classical dynamic Bayesian networks (DBNs) are based on the homogeneous Markov assumption and cannot deal with non-homogeneous temporal processes. Various approaches to relax the homogeneity assumption have recently been proposed.
Husmeier, D. +5 more
core +1 more source
Lazy training of radial basis neural networks [PDF]
, 2006 Proceeding of: 16th International Conference on Artificial Neural Networks, ICANN 2006. Athens, Greece, September 10-14, 2006Usually, training data are not evenly distributed in the input space.
Galván, Inés M. +5 more
core +1 more source
Ex Situ Transfer of Bayesian Neural Networks to Resistive Memory‐Based Inference Hardware
Advanced Intelligent Systems, 2021 Neural networks cannot typically be trained locally in edge‐computing systems due to severe energy constraints. It has, therefore, become commonplace to train them “ex situ” and transfer the resulting model to a dedicated inference hardware.
Thomas Dalgaty +4 more
doaj +1 more source
Predicting the Survival of Gastric Cancer Patients Using Artificial and Bayesian Neural Networks [PDF]
Asian Pac J Cancer Prev, 2018 Introduction and purpose: In recent years the use of neural networks without any premises for investigation of prognosis in analyzing survival data has increased.
Korhani Kangi A, Bahrampour A.
europepmc +2 more sources
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 +4 more sources
Bayesian Neural Network Priors Revisited
CoRR, 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
Continual learning using Bayesian neural networks [PDF]
, 2020 Continual learning models allow them to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios, in which the models are trained using different data with various distributions, neural networks (NNs ...
Enshaeifar, Shirin +3 more
core +1 more source
Using topological data analysis for building Bayesan neural networks
Научно-технический вестник информационных технологий, механики и оптикиFor 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
Spatial Bayesian neural networks
Spatial Statistics35 pages, 21 ...
Andrew Zammit-Mangion +4 more
openaire +4 more sources
Flat Seeking Bayesian Neural Networks
Advances in Neural Information Processing Systems 36, 2023 Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior distribution based on observed data. The model sampled from the posterior distribution can be used for providing ensemble predictions and quantifying prediction uncertainty.
Van-Anh Nguyen +5 more
openaire +4 more sources