Machine translation with the use of deep learning.
Анотація
Deep learning is one of many methods of machine learning that is based on training the data characteristics. Nowadays when considering deep learning we can distinguish three of its historical stages. The first one is related to cybernetics and dates back to the 1940–1960’s, when the theory of biological education was developed and the first models, including the perceptron, which allowed one neuron to be trained, were implemented. The second phase of the 1980–1990’s period is associated with the connectionist approach when the backpropagation method was applied to train a neural network with one or two hidden layers. The third stage – deep learning – started around 2006.Посилання
Федоров Е.Е. Искусственные нейронные сети: монография / Е.Е. Федоров. – Красноармейск: ДВНЗ «ДонНТУ», 2016. – 338 с.
Fedorov E. E. Iskusstvennye neironnye seti: monografiia [Artificial neural networks: a monograph] / E. E. Fedorov. – Krasnoarmeisk: DVNZ «DonNTU», 2016. – 338 s. [in Russian].
Goodfellow, I. et al. Deep learning. Vol. 1. Cambridge: MIT Press, 2016.
Hochreiter, Sepp, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9.8 (1997): 1735-1780.
Hutchins, J. Machine translation: History of research and applications. 1995.
Hutchins, J. The history of machine translation in a nutshell. Retrieved December, 2005, 20: 2009.
Neural Network for Machine Translation, at Production Scale. – Retrieved from: https://ai.googleblog.com/2016/09/a-neural-network-for-machine.html
