CSC321: Neural Networks

Lecture 9: Bayesian learning continued

Bayes Theorem

Maximum A Posteriori Learning

The Bayesian interpretation of weight decay

Full Bayesian Learning

Overfitting: A frequentist illusion?

A classic example of overfitting

Approximating full Bayesian learning in a neural network

An example of full Bayesian learning

Computing the likelihood term for a logistic output unit

What can we do if there are too many parameters for a grid to be feasible?

One method for sampling weight vectors