Results 231 to 240 of about 51,507 (261)

Bayesian Neural Networks

2021
In this chapter, we introduce the concept of Bayesian Neural Network and motivate the reader, presenting its gains over the classical neural networks. We scrutinize four of the most popular algorithms in the area: Bayes by Backprop, Probabilistic Backpropagation, Monte Carlo Dropout, Variational Adam.
Lucas Pinheiro Cinelli, Matheus Araújo Marins, Eduardo Antúnio Barros da Silva, Sérgio Lima Netto   +3 more
openaire   +1 more source

Bayesian Regularization of Neural Networks

2008
Bayesian regularized artificial neural networks (BRANNs) are more robust than standard back-propagation nets and can reduce or eliminate the need for lengthy cross-validation. Bayesian regularization is a mathematical process that converts a nonlinear regression into a "well-posed" statistical problem in the manner of a ridge regression.
Frank, Burden, Dave, Winkler
openaire   +2 more sources

Bayesian evolution of rich neural networks

2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), 2005
In this paper we present a genetic approach that uses a Bayesian fitness function to the design of rich neural network topologies in order to find an optimal domain-specific non-linear function approximator with good generalization performance. Rich neural networks have a feed-forward topology with shortcut connections and arbitrary activation ...
MATTEUCCI, MATTEO, D. Spadoni
openaire   +2 more sources

Compiling Bayesian Networks into Neural Networks

1993
The criticism on the usage of Bayesian Networks in expert systems was centered around the claim that the use of probability requires a massive amount of data in the form of conditional probabilities. This paper shows that given information easily obtained from experts, the dependence model and some observations, the conditional probabilities can be ...
openaire   +1 more source

Bayesian neural networks

Biological Cybernetics, 1989
A neural network that uses the basic Hebbian learning rule and the Bayesian combination function is defined. Analogously to Hopfield's neural network, the convergence for the Bayesian neural network that asynchronously updates its neurons' states is proved.
exaly   +2 more sources

Neural network classification: a Bayesian interpretation

IEEE Transactions on Neural Networks, 1990
The relationship between minimizing a mean squared error and finding the optimal Bayesian classifier is reviewed. This provides a theoretical interpretation for the process by which neural networks are used in classification. A number of confidence measures are proposed to evaluate the performance of the neural network classifier within a statistical ...
exaly   +3 more sources

Bayesian dual neural networks for recommendation

Frontiers of Computer Science, 2019
Most traditional collaborative filtering (CF) methods only use the user-item rating matrix to make recommendations, which usually suffer from cold-start and sparsity problems. To address these problems, on the one hand, some CF methods are proposed to incorporate auxiliary information such as user/item profiles; on the other hand, deep neural networks,
Jia He 0001, Fuzhen Zhuang, Yanchi Liu, Qing He 0003, Fen Lin   +4 more
openaire   +1 more source

Bayesian Neural Networks and Its Application

2008 Fourth International Conference on Natural Computation, 2008
The Bayesian approach provides consistent way to do inference by integrating the evidence from data with prior knowledge from the problem. Bayesian neural networks can overcome the main difficulty of controlling the modelpsilas complexity in modelling building of standard neural network.
Chunling Fan, Feng Gao, Sitong Sun, Fengying Cui   +3 more
openaire   +1 more source

Classification with Bayesian Neural Networks

2006
I submitted entries for the two classification problems — “Catalysis” and “Gatineau” — in the Evaluating Predictive Uncertainty Challenge. My entry for Catalysis was the best one; my entry for Gatineau was the third best, behind two similar entries by Nitesh Chawla.
openaire   +1 more source

Bayesian neural networks with correlating residuals

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), 2003
In a multivariate regression problem it is often assumed that residuals of outputs are independent of each other. In many applications a more realistic model would allow dependencies between the outputs. In this paper we show how a Bayesian treatment using the Markov chain Monte Carlo method can allow for a full covariance matrix with multilayer ...
Aki Vehtari, Jouko Lampinen
openaire   +1 more source