Scholarlink

Abstract <p>The reservoir computing method has attracted much attention owing to its ability to reduce computational complexity by using fixed internal synaptic connections. This study examines a quantized reservoir neural network for use on neuromorphic hardware as a machine learning model for solving time series classification problems. The experiments were conducted on outpatient electrocardiogram recordings. The approach under consideration demonstrates competitive accuracy and robustness and can be considered for use in wearable devices owing to its energy efficiency.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Neuromorphic Reservoir Computing for Heartbeat Classification

  • 期刊论文

  • 发表日期：

    2025年9月1日

查看全文
  • Maxim Igorevich Kostyukov,
  • Lev Alexandrovich Smirnov,
  • Grigoriy Vladimirovich Osipov

摘要

Abstract

The reservoir computing method has attracted much attention owing to its ability to reduce computational complexity by using fixed internal synaptic connections. This study examines a quantized reservoir neural network for use on neuromorphic hardware as a machine learning model for solving time series classification problems. The experiments were conducted on outpatient electrocardiogram recordings. The approach under consideration demonstrates competitive accuracy and robustness and can be considered for use in wearable devices owing to its energy efficiency.