1 code implementation • 22 Jun 2020 • Sean Saito, Eugene Chua, Nicholas Capel, Rocco Hu
Explainability algorithms such as LIME have enabled machine learning systems to adopt transparency and fairness, which are important qualities in commercial use cases.
1 code implementation • 6 Mar 2020 • Sean Saito, Jin Wang
We investigate the problem of identifying adversarial attacks on image-based neural networks.
no code implementations • 1 Dec 2018 • Sean Saito, Sujoy Roy
Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest.
no code implementations • 31 May 2017 • Zhenzhou Wu, Sean Saito
Traditionally, classifying large hierarchical labels with more than 10000 distinct traces can only be achieved with flatten labels.