27–28 May 2021
online
Europe/Copenhagen timezone
Transferring innovative methods across scientific boundaries...

Anomaly Detection using Dimensionality reduction - an Active learning approach.

28 May 2021, 13:30
5m
Poster Images Poster session 2

Speaker

Emmanuel SEKYI (African Institute for Mathematical Sciences, Cape Town)

Description

Anomaly detection can be extremely challenging in real-world situations considering the big data problem. The features that distinguish the anomalies are usually unknown. In this case, standard anomaly detection algorithms may perform very poorly because they are not being fed the correct features. Learning these features even with a few examples of anomalies is challenging. We introduce an algorithm based on dimensionality reduction methods. It learns about primary prototypes in the data while identifies the anomalies by their large distances from the prototypes. Besides, it can identify the anomalies as a new class and get customized to find interesting objects. We evaluated our algorithm on a wide variety of simulated and real datasets, in up to 3000 dimensions. It shows to be robust and highly competitive with commonly-used anomaly detection algorithms, especially in high dimensions.

Primary authors

Emmanuel SEKYI (African Institute for Mathematical Sciences, Cape Town) Alireza VAFAEI SADR (university of Geneva) Dr Bruce BASSETT (African Institute for Mathematical Sciences, Cape Town) Dr Martin KUNZ (Departement de Physique Theorique and Center for Astroparticle Physics, University of Geneva)

Presentation materials