পদ্ধতির তুলনা করুন

	আধা-তত্ত্বাবধানাধীন শিখন (Semi-supervised Learning)	স্ব-পর্যবেক্ষণাধীন শিখন
ক্ষেত্র	যন্ত্র শিখন	যন্ত্র শিখন
পরিবার	Machine learning	Machine learning
উদ্ভবের বছর	1970s–2006 (formalized)	2018–2020
প্রবর্তক	Vapnik, V. N. and others (community of researchers, 1970s–2000s)	LeCun, Y. and community (formalized ~2018–2020)
ধরন	Learning paradigm	Representation learning paradigm
মৌলিক উৎস	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9	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/
অপর নাম	SSL, semi-supervised machine learning, transductive learning, label-efficient learning	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
সম্পর্কিত	5	3
সারসংক্ষেপ	Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained.	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.