The Evolution of Recurrent Neural Networks

There was a point in time where there were three of us in a room in Mando Switzerland, who were the only people in the world using LSTM. Among the three of us by far, Alex Graves has done the most with L STM. He continued after he finished his PhD and he continued doggedly to try to understand how recurrent neural networks worked. It's become like sort of the touchstone for, you know, recurrent models in time series analysis. And it forms some version of it forms the core of what we're doing with translation.