Search Results for author: Arthur da Cunha

Found 2 papers, 0 papers with code

Boosting, Voting Classifiers and Randomized Sample Compression Schemes

no code implementations5 Feb 2024 Arthur da Cunha, Kasper Green Larsen, Martin Ritzert

At the center of this paradigm lies the concept of building the strong learner as a voting classifier, which outputs a weighted majority vote of the weak learners.

Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks

no code implementations ICLR 2022 Arthur da Cunha, Emanuele Natale, Laurent Viennot

The lottery ticket hypothesis states that a randomly-initialized neural network contains a small subnetwork such that, when trained in isolation, can compete with the performance of the original network.

Cannot find the paper you are looking for? You can Submit a new open access paper.