Bayesian MLP neural networks for image analysis

摘要

We demonstrate the advantages of using Bayesian multi-layer perceptron (MLP) neural networks for image analysis. The Bayesian approach provides consistent way to do inference by combining the evidence from the data to prior knowledge from the problem. A practical problem with MLPs is to select the correct complexity for the model, i.e., the right number of hidden units or correct regularization parameters. The Bayesian approach offers efficient tools for avoiding overfitting even with very complex models, and facililales estimation of the confidence intervals of the results. In this contribulion we review the Bayesian melhods for MLPs and present comparison results from two case sludies. In the first case, MLPs were used to solve the inverse problem in electrical impedance tomography. The Bayesian MLP provided consistently better resulls than other methods. In the second case, the goal was to locale trunks of trees in foresl scenes. With Bayesian MLP it was possible to use large number of potentially useful features and prior for determining the relevance of the features automatically.