Unsupervised Clustering of Time Series Signals using Neuromorphic Energy-Efficient Temporal Neural Networks

TL;DR

This paper introduces a neuromorphic, energy-efficient approach for unsupervised time series clustering using Temporal Neural Networks, suitable for low-power edge devices, demonstrating comparable or better performance with minimal hardware resources.

Contribution

The work presents a novel neuromorphic method for unsupervised time series clustering that enables ultra low-power, continuous online learning on edge devices, with detailed hardware efficiency analysis.

Findings

Outperforms or matches existing clustering algorithms in accuracy.

Consumes only 0.005 mm^2 die area and 22 μW power in 7 nm CMOS.

Processes each signal with approximately 5 ns latency.

Abstract

Unsupervised time series clustering is a challenging problem with diverse industrial applications such as anomaly detection, bio-wearables, etc. These applications typically involve small, low-power devices on the edge that collect and process real-time sensory signals. State-of-the-art time-series clustering methods perform some form of loss minimization that is extremely computationally intensive from the perspective of edge devices. In this work, we propose a neuromorphic approach to unsupervised time series clustering based on Temporal Neural Networks that is capable of ultra low-power, continuous online learning. We demonstrate its clustering performance on a subset of UCR Time Series Archive datasets. Our results show that the proposed approach either outperforms or performs similarly to most of the existing algorithms while being far more amenable for efficient hardware implementation. Our hardware assessment analysis shows that in 7 nm CMOS the proposed architecture, on average, consumes only about 0.005 mm^2 die area and 22 uW power and can process each signal with about 5 ns latency.