ScholarGate
Асистент

Порівняння методів

Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.

Трансферне навчання×Самокероване навчання×
ГалузьМашинне навчанняМашинне навчання
РодинаMachine learningMachine learning
Рік появи2010 (formalized); 1990s (early roots)2018–2020
Автор методуPan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)LeCun, Y. and community (formalized ~2018–2020)
ТипLearning paradigmRepresentation learning paradigm
Основоположне джерелоPan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗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/ link ↗
Інші назвиTL, domain adaptation, fine-tuning, pre-trained model adaptationSSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Пов'язані33
ПідсумокTransfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.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.
ScholarGateНабір даних
  1. v1
  2. 2 Джерела
  3. PUBLISHED
  1. v1
  2. 2 Джерела
  3. PUBLISHED

Перейти до пошуку Download slides

ScholarGateПорівняння методів: Transfer Learning · Self-supervised Learning. Отримано 2026-06-15 з https://scholargate.app/uk/compare