2017

Discrete Event, Continuous Time RNNs

Mozer, Michael C., Kazakov, Denis, Lindsey, Robert V.

Understand

We investigate recurrent neural network architectures for event-sequence processing.

  • Event sequences, characterized by discrete observations stamped with continuous-valued times of occurrence, are challenging due to the potentially wide dynamic range of relevant time scales as well as interactions between time scales.
  • We describe four forms of inductive bias that should benefit architectures for event sequences: temporal locality, position and scale homogeneity, and scale interdependence.
  • We extend the popular gated recurrent unit (GRU) architecture to incorporate these biases via intrinsic temporal dynamics, obtaining a continuous-time GRU.

Reading the bibliography…