Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline

TL;DR

This paper introduces a simple, end-to-end deep neural network baseline for time series classification that achieves competitive performance without heavy preprocessing, serving as a strong foundation for future research.

Contribution

The paper presents a pure deep learning baseline using Fully Convolutional Networks and ResNet structures for time series classification, emphasizing simplicity and strong performance.

Findings

FCN achieves state-of-the-art results

Deep ResNet models are competitive

Global average pooling enables interpretability

Abstract

We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy preprocessing on the raw data or feature crafting. The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and our exploration of the very deep neural networks with the ResNet structure is also competitive. The global average pooling in our convolutional model enables the exploitation of the Class Activation Map (CAM) to find out the contributing region in the raw data for the specific labels. Our models provides a simple choice for the real world application and a good starting point for the future research. An overall analysis is provided to discuss the generalization capability of our models, learned features, network structures and the classification semantics.