ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

TL;DR

ROCKET introduces a fast and accurate time series classification method using random convolutional kernels, achieving state-of-the-art results with significantly reduced computational cost compared to existing approaches.

Contribution

The paper presents a novel approach that employs random convolutional kernels with simple linear classifiers, drastically improving speed while maintaining high accuracy in time series classification.

Findings

Achieves state-of-the-art accuracy on multiple datasets.

Reduces training time significantly compared to existing methods.

Uses random kernels with linear classifiers for efficiency.

Abstract

Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets. Additionally, many existing methods focus on a single type of feature such as shape or frequency. Building on the recent success of convolutional neural networks for time series classification, we show that simple linear classifiers using random convolutional kernels achieve state-of-the-art accuracy with a fraction of the computational expense of existing methods.