RonRichman

t1 <- torch_tensor(array(1:50, dim = c(2, 25)))
t1[1,]

batch_size <- 2
no_embeds = 5
embed_dim = 5

t1_reshape <- torch_unsqueeze(t1,3)
t1_reshape2 <- torch_reshape(t1_reshape,c(batch_size, no_embeds, embed_dim))
t1_reshape3 <- torch_transpose(t1_reshape2,2,1)

RonRichman

Bahdanau, D., K. Cho and Y. Bengio. 2014. "Neural machine translation by jointly learning to align and translate", arXiv preprint arXiv:1409.0473 
Bengio, Y. 2009. "Learning deep architectures for AI", Foundations and trends® in Machine Learning 2(1):1-127.
Bengio, Y. 2012. "Deep learning of representations for unsupervised and transfer learning," Paper presented at Proceedings of ICML Workshop on Unsupervised and Transfer Learning. 17-36.
Bengio, Y., A. Courville and P. Vincent. 2013. "Representation learning: A review and new perspectives", IEEE transactions on pattern analysis and machine intelligence 35(8):1798-1828.
Brass, W. 1964. "Uses of census or survey data for the estimation of vital rates", Paper presented at African Seminar on Vital Statistics. Addis Ababa, 14-19 December 1964. United Nations. 
Breeden, J.L. and E. Leonova. 2019. "When Big Data Isn’t Enough: Solving the long-range forecasting problem in supervised learning," Paper presented at 2019 International Conference on Modeling, Simulation