Title:
ANOMALY DETECTION DEVICE USING NEURAL NETWORK LEARNED USING HETEROGENEOUS LOSS FUNCTION
Document Type and Number:
WIPO Patent Application WO/2024/071728
Kind Code:
A1
Abstract:
An anomaly detection device is disclosed. The anomaly detection device using a heterogeneous loss function, according to one embodiment, comprises: a receiver for receiving data from which normality or anomaly is to be detected; and a processor for detecting whether an anomaly exists in the data, by inputting the data into a pre-learned neural network, wherein the pre-learned neural network can be learned through a heterogeneous loss function calculated using a gradient parameter determined on the basis of an anomaly score.
Inventors:
YOO KWANGSUN (KR)
LEE JUNGI (KR)
LEE JUNGI (KR)
Application Number:
PCT/KR2023/013473
Publication Date:
April 04, 2024
Filing Date:
September 08, 2023
Export Citation:
Assignee:
EL ROI LAB INC (KR)
International Classes:
G06N3/08; G06F11/22; G06F11/277; G06F17/18; G06N3/04
Foreign References:
| KR20220022329A | 2022-02-25 | |||
| KR20200120622A | 2020-10-21 |
Other References:
ANONYMOUS: "HETEROGENEOUS LOSS FUNCTION WITH AGGRES-SIVE REJECTION FOR CONTAMINATED DATA IN ANOMALY DETECTION", CONFERENCE PAPER AT ICLR 2023, 22 September 2022 (2022-09-22), pages 1 - 19, XP093155218, Retrieved from the Internet
"Topics in cryptology - CT-RSA 2020 : the Cryptographers' Track at the RSA Conference 2020, San Francisco, CA, USA, February 24-28, 2020", vol. 13, 30 April 2020, SPRINGER, 201 Olin Library Cornell University Ithaca, NY 14853, article BEGGEL LAURA; PFEIFFER MICHAEL; BISCHL BERND: "Robust Anomaly Detection in Images Using Adversarial Autoencoders", pages: 206 - 222, XP047550313, DOI: 10.1007/978-3-030-46150-8_13
CHEN QIU; AODONG LI; MARIUS KLOFT; MAJA RUDOLPH; STEPHAN MANDT: "Latent Outlier Exposure for Anomaly Detection with Contaminated Data", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 16 February 2022 (2022-02-16), 201 Olin Library Cornell University Ithaca, NY 14853, XP091160927
"Topics in cryptology - CT-RSA 2020 : the Cryptographers' Track at the RSA Conference 2020, San Francisco, CA, USA, February 24-28, 2020", vol. 13, 30 April 2020, SPRINGER, 201 Olin Library Cornell University Ithaca, NY 14853, article BEGGEL LAURA; PFEIFFER MICHAEL; BISCHL BERND: "Robust Anomaly Detection in Images Using Adversarial Autoencoders", pages: 206 - 222, XP047550313, DOI: 10.1007/978-3-030-46150-8_13
CHEN QIU; AODONG LI; MARIUS KLOFT; MAJA RUDOLPH; STEPHAN MANDT: "Latent Outlier Exposure for Anomaly Detection with Contaminated Data", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 16 February 2022 (2022-02-16), 201 Olin Library Cornell University Ithaca, NY 14853, XP091160927
Attorney, Agent or Firm:
YOUNGBEE INTELLECTUAL PROPERTY (KR)
Download PDF: