RULLS: Randomized Union of Locally Linear Subspaces for Feature Engineering

no code implementations • 25 Apr 2018 • Namita Lokare, Jorge Silva, Ilknur Kaynar Kabul

In this paper, we propose a robust feature engineering method, Randomized Union of Locally Linear Subspaces (RULLS).

Clustering Feature Engineering +1

Multi-Task Learning with Incomplete Data for Healthcare

no code implementations • 6 Jul 2018 • Xin J. Hunt, Saba Emrani, Ilknur Kaynar Kabul, Jorge Silva

Multi-task learning is a type of transfer learning that trains multiple tasks simultaneously and leverages the shared information between related tasks to improve the generalization performance.

Imputation Multi-Task Learning

Localized Uncertainty Attacks

no code implementations • 17 Jun 2021 • Ousmane Amadou Dia, Theofanis Karaletsos, Caner Hazirbas, Cristian Canton Ferrer, Ilknur Kaynar Kabul, Erik Meijer

Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain.