مقایسهٔ روش‌ها

	LSTM	ترانسفورمر چندوجهی
حوزه	یادگیری عمیق	یادگیری عمیق
خانواده	Machine learning	Machine learning
سال پیدایش	1997	2019–2021
پدیدآور	Hochreiter, S. & Schmidhuber, J.	Lu et al. (ViLBERT); Radford et al. (CLIP)
نوع	Recurrent neural network (gated memory cell)	Cross-modal attention-based deep learning model
منبع بنیادین	Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.	Lu, J., Batra, D., Parikh, D., & Lee, S. (2019). ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. Advances in Neural Information Processing Systems (NeurIPS), 32.
نام‌های دیگر	LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
مرتبط	5	5
خلاصه	LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps.	A Multimodal Transformer extends the standard Transformer architecture to process and jointly reason over two or more input modalities — most commonly text and images, but also audio, video, or structured data. Cross-modal attention layers allow information from one modality to inform representations in another, enabling tasks such as visual question answering, image captioning, and multimodal sentiment analysis.