قارن الطرق

	التجميع الذاتي باستخدام خوارزمية K-means	التعلم ذاتي الإشراف
المجال	تعلم الآلة	تعلم الآلة
العائلة	Machine learning	Machine learning
سنة النشأة	2018	2018–2020
صاحب الطريقة	Caron, M. et al. (DeepCluster framework)	LeCun, Y. and community (formalized ~2018–2020)
النوع	Self-supervised clustering	Representation learning paradigm
المصدر التأسيسي	Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018). Deep Clustering for Unsupervised Learning of Visual Features. In Proceedings of the European Conference on Computer Vision (ECCV), 132–149.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
الأسماء البديلة	self-supervised clustering with K-means, deep clustering with K-means, unsupervised K-means with pseudo-labels, SSL K-means	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
ذات صلة	5	3
الملخص	Self-supervised K-means is a clustering technique that combines K-means assignment with self-supervised representation learning. The model alternates between clustering unlabeled data points into K groups and using those cluster assignments as pseudo-labels to refine an underlying feature representation, yielding increasingly coherent clusters without any human-annotated ground truth.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.