Deep Learning on Bad Time Series Data: Corrupt, Sparse, Irregular and Ugly

2020-10-22T09:53:03+00:00

How do you train neural networks on time series that are non-uniformly sampled,  irregularly sampled, have non-equidistant timesteps, or have missing or corrupt values? In the following post, I try to summarize and point to effective methods for dealing with such data.

How do you train neural networks on time series that are non-uniformly sampled, irregularly sampled, have non-equidistant timesteps, or have missing or corrupt values