পদ্ধতির তুলনা করুন

	Bayesian Active Learning	ফিউ-শট লার্নিং
ক্ষেত্র	যন্ত্র শিখন	যন্ত্র শিখন
পরিবার	Machine learning	Machine learning
উদ্ভবের বছর	1992–2011	2011–2017
প্রবর্তক	MacKay, D.J.C.; Houlsby, N. et al.	Lake, B. M.; Vinyals, O.; Finn, C. et al.
ধরন	Active learning with Bayesian uncertainty	Meta-learning / low-data learning paradigm
মৌলিক উৎস	Houlsby, N., Huszár, F., Ghahramani, Z., & Lengyel, M. (2011). Bayesian Active Learning for Classification and Preference Learning. arXiv preprint arXiv:1112.5745.	Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29.
অপর নাম	BAL, Bayesian optimal experimental design for ML, BALD (Bayesian Active Learning by Disagreement), probabilistic active learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
সম্পর্কিত	6	4
সারসংক্ষেপ	Bayesian Active Learning (BAL) combines a probabilistic model with an active query strategy to identify the unlabeled examples that, once labeled, would most reduce model uncertainty. Instead of labeling data at random, BAL guides an oracle — typically a human annotator — toward the points where labeling will provide the greatest information gain, making it highly label-efficient.	Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited.