Deep Neural Network Ensembles for Time Series Classification
This work addresses the problem of underperformance in deep learning for time series classification, offering a competitive solution for researchers and practitioners in the field, though it is incremental as it builds on existing ensemble methods.
The paper tackled the performance gap of neural networks in time series classification by proposing a neural network ensemble of 60 models, which significantly improved state-of-the-art neural network performance on the UCR/UEA archive and matched HIVE-COTE.
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.