Инновационный центр «Сколково», Москва, Россия
16 апреля 2019 г.
Инновационный центр «Сколково», Москва, Россия | 16 апреля 2019 г.

Обнаружение отклонений от нормального состояния, основанных на генерации выброса в точке отсчёта

Марк Сканави
10:00 10:30

Anomaly detection suffers from unbalanced data since anomalies are quite rare. Generating artificial anomalies is a solution to such ill or not fully defined data. However, synthesis requires an expressive representation to guarantee the quality of the generated data. In this talk, I will present a two-level hierarchical latent space representation that distills inliers’ feature-descriptors into more robust representations based on a variational family of distributions for zero-shot anomaly generation. From the learned latent distributions of inliers, we select those that lie on the outskirts of the training data as synthetic-outlier generators, and we synthesize from them, i.e., generate negative samples without seeing them before, to train binary classifiers. We found that the proposed method allows us to synthesize pseudo outlier samples effectively, and in turn, train robust binary classifiers for outlier detection (without the need for real outliers during training)

Следующее мероприятие в этом зале

Роботы, создающие новые молекулы

Марк Сканави
10:30 11:00

Спикер

Доцент,
Университет Иннополис