EE Seminar: Two-Step Disentanglement

Speaker: Naama Hadad

M.Sc. student under the supervision of Prof. Lior Wolf

Wednesday, July 12th, 2017 at 15:00

Room 011, Kitot Bldg., Faculty of Engineering

Two-Step Disentanglement

In this work we address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not. Our solution is simpler than previous solutions and employs neural network with adversarial training in a straightforward manner. We demonstrate the new method on visual datasets as well as on financial data. In order to evaluate our results we use previous evaluation methods for visual disentanglement and a hypothetical trading strategy whose performance is affected by the performance of the disentanglement.