Machine learningMachine learning

Robusni autoenkoder za detekciju anomalija

Robusni autoenkoder za detekciju anomalija proširuje standardni okvir autoenkodera mehanizmima robusnosti — kao što su razlaganje na retke (sparse decomposition), robusne funkcije gubitka (loss functions) ili adverzarijalna regularizacija — tako da model uči kompaktnu reprezentaciju normalnog ponašanja, ostajući istovremeno otporan na koruptivni uticaj anomalija ugrađenih u podatke za obuku.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Zhou, C., & Paffenroth, R. C. (2017). Anomaly detection with robust deep autoencoders. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 665–674). ACM. DOI: 10.1145/3097983.3098052
  2. Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Robust Autoencoder-Based Anomaly Detection. ScholarGate. https://scholargate.app/sr/machine-learning/robust-autoencoder-anomaly-detection

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateRobust Autoencoder anomaly detection (Robust Autoencoder-Based Anomaly Detection). Preuzeto 2026-06-15 sa https://scholargate.app/sr/machine-learning/robust-autoencoder-anomaly-detection · Skup podataka: https://doi.org/10.5281/zenodo.20539026