Porovnat metody

	Samo-dohledové GRU	Polo-dohledová GRU
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2014–2019	2014–2015
Tvůrce	Cho, K. et al. (GRU); self-supervised training paradigm from broader SSL literature	Dai, A. M. & Le, Q. V. (semi-supervised sequence learning); Cho, K. et al. (GRU architecture)
Typ	Self-supervised sequence model	Semi-supervised sequence model
Původní zdroj	Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014.	Dai, A. M., & Le, Q. V. (2015). Semi-supervised Sequence Learning. Advances in Neural Information Processing Systems (NeurIPS), 28.
Další názvy	SS-GRU, Self-supervised Gated Recurrent Unit, GRU with self-supervised pretraining, Unsupervised GRU pretraining	Semi-supervised GRU, SSL-GRU, GRU with unlabeled data, semi-supervised recurrent classifier
Příbuzné	4	5
Shrnutí	Self-supervised GRU trains a Gated Recurrent Unit network using automatically constructed supervision signals — such as next-step prediction or masked token recovery — derived from the unlabeled data itself. The learned sequence representations are then fine-tuned on small labeled datasets, making high-quality sequential modeling feasible when annotations are scarce.	Semi-supervised GRU applies the Gated Recurrent Unit architecture to settings where only a small fraction of sequential data is labeled. By first pre-training or jointly training on abundant unlabeled sequences — through language modeling, auto-encoding, or consistency regularization — and then fine-tuning on labeled examples, the model exploits the full corpus to learn richer sequence representations than supervised-only training would allow.