NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:2058
Title:Learning Representations for Time Series Clustering

This paper proposes a deep learning approach to clustering time series by combining a deep auto encoder and the spectral relaxation of K-means. The reviewers found the approach novel and the experimental evaluation of the approach reasonable. The concerns that the reviewers raised were addressed by the authors in their response. The authors should incorporate the suggestions that the reviewers provided to improve their paper for the camera-ready version.