← Search

Philippe Donnat

2 accepted papers

2018

Autoregressive Convolutional Neural Networks for Asynchronous Time Series

ICML 2018oral

We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks. It involves an AR-like…