# Deep Neural Network Ensembles for Time Series Classification

## TL;DR

This paper demonstrates that an ensemble of 60 deep neural networks significantly outperforms existing neural network approaches and rivals the top ensemble methods in time series classification, using the UCR/UEA benchmark.

## Contribution

The paper introduces a novel neural network ensemble (NNE) that surpasses previous neural network methods and matches the performance of top ensemble classifiers in TSC.

## Key findings

- NNE outperforms previous neural network models on UCR/UEA datasets.
- NNE surpasses COTE and matches HIVE-COTE performance.
- Ensembling deep neural networks improves TSC accuracy significantly.

## Abstract

Deep neural networks have revolutionized many fields such as computer vision and natural language processing. Inspired by this recent success, deep learning started to show promising results for Time Series Classification (TSC). However, neural networks are still behind the state-of-the-art TSC algorithms, that are currently composed of ensembles of 37 non deep learning based classifiers. We attribute this gap in performance due to the lack of neural network ensembles for TSC. Therefore in this paper, we show how an ensemble of 60 deep learning models can significantly improve upon the current state-of-the-art performance of neural networks for TSC, when evaluated over the UCR/UEA archive: the largest publicly available benchmark for time series analysis. Finally, we show how our proposed Neural Network Ensemble (NNE) is the first time series classifier to outperform COTE while reaching similar performance to the current state-of-the-art ensemble HIVE-COTE.