Deep Temporal Clustering : Fully Unsupervised Learning of Time-Domain Features

Understand

Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning.

• Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and temporal clustering into a single end-to-end learning framework, fully unsupervised.
• The algorithm utilizes an autoencoder for temporal dimensionality reduction and a novel temporal clustering layer for cluster assignment.
• Then it jointly optimizes the clustering objective and the dimensionality reduction objec tive.