Sammenlign metoder

	Multimodal LSTM	Gated Recurrent Unit (GRU)
Fagfelt	Dyp læring	Dyp læring
Familie	Machine learning	Machine learning
Opprinnelsesår	2016	2014
Opphavsperson	Rajagopalan et al. and various concurrent works (2016–2018)	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
Type	Recurrent neural network architecture	Recurrent neural network with gating
Opprinnelig kilde	Rajagopalan, S., Tran, L., Rozgic, V., Narayanan, S., Kumar, A., & Ramakrishna, S. (2016). Extending Long Short-Term Memory for Multi-View Structured Learning. In Proceedings of ECCV 2016. Springer.	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.
Alias	MM-LSTM, multimodal recurrent network, multi-input LSTM, multimodal sequence model	GRU, GRU network, gated RNN, GRU cell
Relaterte	4	3
Sammendrag	Multimodal LSTM extends the standard Long Short-Term Memory network to jointly process sequential data from multiple input modalities — such as text, audio, and video — within a unified recurrent architecture. By fusing representations from different sources before or within the LSTM cells, it captures temporal dependencies that span and cross modalities, making it a foundational approach for tasks like sentiment analysis, video captioning, and affective computing.	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.