Počet záznamů: 1
Density-Approximating Neural Network Models for Anomaly Detection
- 1.
SYSNO ASEP 0507118 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název Density-Approximating Neural Network Models for Anomaly Detection Tvůrce(i) Flusser, M. (CZ)
Pevný, T. (CZ)
Somol, Petr (UTIA-B) RIDCelkový počet autorů 3 Zdroj.dok. ACM SIGKDD 2018 Workshop. - New York : ACM, 2018 - ISBN 978-1-4503-5552-0 Rozsah stran s. 1-8 Poč.str. 8 s. Forma vydání Online - E Akce ACM SIGKDD 2018 Workshop Datum konání 20.08.2018 Místo konání London Země GB - Velká Británie Typ akce WRD Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova neural network ; anomaly detection Vědní obor RIV BC - Teorie a systémy řízení Obor OECD Robotics and automatic control Institucionální podpora UTIA-B - RVO:67985556 Anotace We propose an alternative use of neural models in anomaly detection. Traditionally, in anomaly detection context the common use of neural models is in form of auto-encoders. Through the use of auto-encoders the true anomality is proxied by reconstruction error. Auto-encoders often perform well but do not guarantee to perform as expected in all cases. A popular more direct way of modeling anomality distribution is through k-Nearest Neighbor models. Although kNN can perform better than auto-encoders in some cases, their applicability can be seriously impaired by their space and time complexity especially with high-dimensional large-scale data. The alternative we propose is to model the distribution imposed by kNN using neural networks. We show that such neural models are capable of achieving comparable accuracy to kNN while reducing computational complexity by orders of magnitude. The de-noising e ect of a neural model with limited number of neurons and layers is shown to lead to accuracy improvements in some cases. We evaluate the proposed idea against standard kNN and auto-encoders on a large set of benchmark data and show that in majority of cases it is possible to improve on accuracy or computational cost. Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2020
Počet záznamů: 1