bayesian backpropagation
Bayesian Backpropagation Over I-O Functions Rather Than Weights
The conventional Bayesian justification of backprop is that it finds the MAP weight vector. As this paper shows, to find the MAP i-o function instead one must add a correction tenn to backprop.
Bayesian Backpropagation Over I-O Functions Rather Than Weights
The conventional Bayesian justification of backprop is that it finds the MAP weight vector. As this paper shows, to find the MAP io function instead one must add a correction tenn to backprop. That tenn biases one towards io functions with small description lengths, and in particular favors (somekinds of) feature-selection, pruning, and weight-sharing.
Bayesian Backpropagation Over I-O Functions Rather Than Weights
The conventional Bayesian justification of backprop is that it finds the MAP weight vector. As this paper shows, to find the MAP io function instead one must add a correction tenn to backprop. That tenn biases one towards io functions with small description lengths, and in particular favors (some kinds of) feature-selection, pruning, and weight-sharing.
Bayesian Backpropagation Over I-O Functions Rather Than Weights
The conventional Bayesian justification of backprop is that it finds the MAP weight vector. As this paper shows, to find the MAP io function instead one must add a correction tenn to backprop. That tenn biases one towards io functions with small description lengths, and in particular favors (some kinds of) feature-selection, pruning, and weight-sharing.