Recorded at the ML in PL 2019 Conference, the University of Warsaw, 22-24 November 2019.

Jakub Tomczak (Vrije Universiteit Amsterdam/Qualcomm AI Research Amsterdam)

Slides available at: [ Ссылка ]

Abstract:
Deep learning achieves state-of-the-art results in tasks like image or audio classification. However, adding noise to data can easily fool a deep learning model. During this talk, we will discuss a possible remedy to this issue, namely, learning generative models. We will start with a motivating example of image classification and highlight that training a joint distribution over a label and an object (image) is crucial for uncertainty quantification. Next, we will outline different approaches to model a distribution over objects (e.g., images). More specifically, we will focus on Variational Auto-Encoders and Flow-based models, which are models that allow to learn (approximate) probability distributions. In the conclusion, we will show successes and failures of these models, indicating possible future research directions.

свернуть