Search Results for author:
Found 2 papers, 0 papers with code
PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations
Considering a probability distribution over parameters is known as an efficient strategy to learn a neural network with non-differentiable activation functions.
Efficient Learning of Ensembles with QuadBoost
We first present a general risk bound for ensembles that depends on the Lp norm of the weighted combination of voters which can be selected from a continuous set.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
