השוואת שיטות

	זיהוי אנומליות באמצעות אוטואנקודר למידה עצמית	זיהוי אנומליות באמצעות אוטואנקודר
תחום	למידת מכונה	למידת מכונה
משפחה	Machine learning	Machine learning
שנת המקור	2018–2020	2006–2014
הוגה השיטה	Golan & El-Yaniv; broader self-supervised anomaly detection community	Hinton, G. E. & Salakhutdinov, R. R. (autoencoders); applied to anomaly detection through multiple authors in the 2010s
סוג	Unsupervised / self-supervised deep learning	Unsupervised deep learning (reconstruction-based)
מקור מכונן	Golan, I. & El-Yaniv, R. (2018). Deep one-class classification via geometric transformations. Advances in Neural Information Processing Systems (NeurIPS), 31.	Chalapathy, R. & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407.
כינויים	SSL Autoencoder anomaly detection, self-supervised reconstruction anomaly detection, pretext-task autoencoder anomaly detection, contrastive autoencoder anomaly detection	AE anomaly detection, reconstruction-error anomaly detection, deep autoencoder outlier detection, unsupervised autoencoder anomaly detection
קשורות	6	3
תקציר	Self-supervised autoencoder anomaly detection trains an autoencoder using self-supervised pretext tasks — such as predicting geometric transformations or solving jigsaw puzzles — on unlabeled normal data, then flags as anomalous any input whose reconstruction error or pretext-task score deviates substantially from the learned normal distribution.	Autoencoder anomaly detection trains a neural network to compress and then reconstruct normal data. Because the model has only ever learned what normal looks like, anomalous inputs produce noticeably higher reconstruction errors — and those errors become the anomaly score. The method requires no labeled anomalies and scales naturally to high-dimensional data such as sensor streams, images, and log records.