A recurrent neural network has the capacity to have two inputs: a T-1 immediate output from itself and a given input. This means that the order of information given to a RNN is important. Because of their internal memory and time dependence, this network is preferred in speech recognition, language modeling, and translation.
Polychord. a cutting edge tool for solving big, complex data problems.
Invented in 2017 by two cambridge professors of astrophysics.