Dynamic Time Warping (DTW) is widely used as a similarity measure in various domains. Due to its invariance against warping in the time axis, DTW provides more meaningful discrepancy measurements between two signals than other distance measures. In this paper, we propose a novel component in an artificial neural network. In contrast to the previous successful usage of DTW as a loss function, the proposed framework leverages DTW to obtain a better feature extraction. For the first time, the DTW loss is theoretically analyzed, and a stochastic backpropogation scheme is proposed to improve the accuracy and efficiency of the DTW learning. We also demonstrate that the proposed framework can be used as a data analysis tool to perform data decomposition.

There are many papers that have tried to combine DTW and neural networks, but the alternating optimization approach in this paper appears to be new and significant to me. While the idea of the paper is exciting, the execution is poor and the writing is disappointing. Here are the main feedback points: 1. The writing omits the description of many notations. For example, I could not find the definition of the forward pass for the main network G_{x, w}.

The paper proposes an approach for incorporating Dynamic Time Warping kernels in a neural network. The method is shown to perform well on both synthetic and real data. The reviewers think that this is a novel and potentially impactful contribution to the community. The concerns raised by the reviewers were successfully addressed by the authors or clarified during the discussion. We encourage the authors to improve the presentation of the paper and to add the results as indicated in the rebuttal.

Dynamic Time Warping (DTW) is widely used as a similarity measure in various domains. Due to its invariance against warping in the time axis, DTW provides more meaningful discrepancy measurements between two signals than other dis- tance measures. In this paper, we propose a novel component in an artificial neural network. In contrast to the previous successful usage of DTW as a loss function, the proposed framework leverages DTW to obtain a better feature extraction. For the first time, the DTW loss is theoretically analyzed, and a stochastic backpropogation scheme is proposed to improve the accuracy and efficiency of the DTW learning.

Dynamic Time Warping (DTW) is widely used as a similarity measure in various domains. Due to its invariance against warping in the time axis, DTW provides more meaningful discrepancy measurements between two signals than other dis- tance measures. In this paper, we propose a novel component in an artificial neural network. In contrast to the previous successful usage of DTW as a loss function, the proposed framework leverages DTW to obtain a better feature extraction. For the first time, the DTW loss is theoretically analyzed, and a stochastic backpropogation scheme is proposed to improve the accuracy and efficiency of the DTW learning.