Usporedite metode

	Objašnjivi GRU	Gated Recurrent Unit (GRU)
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2014 (GRU); 2016–2017 (XAI integration)	2014
Tvorac	Cho, K. et al. (GRU); explainability layer via Lundberg & Lee (SHAP) and Ribeiro et al. (LIME)	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
Vrsta	Recurrent neural network with post-hoc or attention-based interpretability	Recurrent neural network with gating
Temeljni izvor	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of EMNLP 2014, 1724–1734.	Cho, K., van Merrienboer, 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, pp. 1724–1734.
Drugi nazivi	XAI-GRU, Interpretable GRU, GRU with explainability, Transparent GRU	GRU, GRU network, gated RNN, GRU cell
Srodne	5	3
Sažetak	Explainable GRU pairs the Gated Recurrent Unit, a compact and efficient recurrent architecture, with explainability techniques such as SHAP, LIME, or attention weighting to reveal which time steps and features drove each prediction. It brings interpretability to sequential modelling without sacrificing the GRU's ability to capture temporal dependencies.	The Gated Recurrent Unit (GRU), introduced by Cho et al. in 2014, is a streamlined recurrent neural network that uses two learned gates — an update gate and a reset gate — to selectively retain or discard information across time steps, enabling effective sequence modelling with fewer parameters than LSTM.