Type
ThesisAuthors
Alfarra, Motasem
Advisors
Ghanem, Bernard
Committee members
Heidrich, Wolfgang
Zhang, Xiangliang

Program
Electrical EngineeringDate
2020-04Permanent link to this record
http://hdl.handle.net/10754/662473
Metadata
Show full item recordAbstract
This thesis tackles the problem of understanding deep neural network with piece- wise linear activation functions. We leverage tropical geometry, a relatively new field in algebraic geometry to characterize the decision boundaries of a single hidden layer neural network. This characterization is leveraged to understand, and reformulate three interesting applications related to deep neural network. First, we give a geo- metrical demonstration of the behaviour of the lottery ticket hypothesis. Moreover, we deploy the geometrical characterization of the decision boundaries to reformulate the network pruning problem. This new formulation aims to prune network pa- rameters that are not contributing to the geometrical representation of the decision boundaries. In addition, we propose a dual view of adversarial attack that tackles both designing perturbations to the input image, and the equivalent perturbation to the decision boundaries.Citation
Alfarra, M. (2020). Applications of Tropical Geometry in Deep Neural Networks. KAUST Research Repository. https://doi.org/10.25781/KAUST-CDBHKae974a485f413a2113503eed53cd6c53
10.25781/KAUST-CDBHK