Approximate algorithms for neural-Bayesi
β
Tom Heskes; Bart Bakker; Bert Kappen
π
Article
π
2002
π
Elsevier Science
π
English
β 240 KB
We describe two speciΓΏc examples of neural-Bayesian approaches for complex modeling tasks: survival analysis and multitask learning. In both cases, we can come up with reasonable priors on the parameters of the neural network. As a result, the Bayesian approaches improve their (maximum likelihood) f