PP: Soft-DTW: a differentiable loss function for time-series

Problem: new loss

Label: new loss;

Abstract:

A differentiable learning loss;

Introduction:

supervised learning: learn a mapping that links an input to an output object.

output object is a time series.

Prediction: two multi-layer perceptrons, the first use Euclidean loss and the second use soft-DTW as a loss function. --------> soft-DTW, better sharp changes.

DTW computes the best possible alignment between two time series.