Bayesian Learning for Neural Networks
Springer Science & Business Media, 6 gru 2012 - 204
Artificial "neural networks" are widely used as flexible models for classification and regression applications, but questions remain about how the power of these models can be safely exploited when training data is limited. This book demonstrates how Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional training methods. Insight into the nature of these complex Bayesian models is provided by a theoretical investigation of the priors over functions that underlie them. A practical implementation of Bayesian neural network learning using Markov chain Monte Carlo methods is also described, and software for it is freely available over the Internet. Presupposing only basic knowledge of probability and statistics, this book should be of interest to researchers in statistics, engineering, and artificial intelligence.
Co mówią ludzie - Napisz recenzję
Nie znaleziono żadnych recenzji w standardowych lokalizacjach.
Inne wydania - Wyświetl wszystko
ARD model autocorrelations Bayesian inference Bayesian learning Bayesian neural network canonical distribution chain Monte Carlo Chapter conditional distribution converge data sets equation equilibrium distribution fractional Brownian functions drawn Gamma distribution Gamma prior Gaussian approximation Gaussian distributions Gaussian priors Gibbs sampling updates given hidden units hidden-to-output weights hybrid Monte Carlo hyperparameters input unit irrelevant inputs likelihood MacKay Markov chain Monte Metropolis algorithm momentum variables Monte Carlo algorithm Monte Carlo implementation Monte Carlo method Monte Carlo updates multilayer perceptron network parameters neural network neural network models noise number of hidden obtained output units partial gradients performance posterior distribution predictive distribution prior distribution procedure random walk rejection rate robot arm problem sampling phase Section simple Metropolis squared error stable distribution standard deviation stepsize adjustment factor super-transitions t-distribution tanh hidden units test error test set training data training set trajectory length vague priors variance weights and biases window zero