Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets

Arthur da Cunha, Université Côte d'Azur, Inria, CNRS, I3S, Aarhus University, Aarhus, Denmark, dac@cs.au.dk, "3026 Francesco d'Amore, Aalto University, Bocconi University, Espoo, Finland, francesco.damore@aalto.fi "3026 Emanuele Natale, Université Côte d'Azur, Inria, CNRS, I3S, Sophia Antipolis, France, emanuele.natale@inria.fr

Neural Information Processing Systems 

The left side shows the effect of pruning of neurons in the weight-matrix of afully-connected layer. The rows in white correspond to neurons pruned in theassociated layer while thecolumns inwhite represent theeffectofremoving neurons from the previous layers. On the right, we allude to the possibility of collapsing the pruned matrix into a smaller,denseone.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found