Salīdzināt metodes

	Pašuzraudzēts Gausa process	Pašuzraudzības apmācība
Nozare	Mašīnmācīšanās	Mašīnmācīšanās
Saime	Machine learning	Machine learning
Izcelsmes gads	2019–2021	2018–2020
Autors	Fortuin, V. et al.; broader self-supervised GP literature	LeCun, Y. and community (formalized ~2018–2020)
Tips	Probabilistic model (self-supervised GP pretraining + kernel learning)	Representation learning paradigm
Pirmavots	Fortuin, V., Rätsch, G., & Mandt, S. (2020). GP-VAE: Deep probabilistic time series imputation using Gaussian process variational autoencoders. Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 108, 1651–1661.	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/
Citi nosaukumi	SSL-GP, self-supervised GP, self-supervised GPR, self-supervised Gaussian process regression	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Saistītās	6	3
Kopsavilkums	Self-supervised Gaussian Process (SSL-GP) combines the principled uncertainty quantification of Gaussian processes with self-supervised pretraining, learning expressive kernels or latent representations from unlabeled data before fitting a GP on a small labeled set. This makes the approach especially powerful in low-labeled-data regimes where a conventional GP would overfit or produce poorly calibrated uncertainty estimates.	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.