Scholarlink

<p>Artificial neural networks have advanced due to scaling dimensions, but conventional computing struggles with inefficiencies due to memory bottlenecks. In-memory computing architectures using memristor devices offer promise but face challenges due to hardware non-idealities. This work proposes layer ensemble averaging—a hardware-oriented fault tolerance scheme for improving inference performance of non-ideal memristive neural networks programmed with pre-trained solutions. Simulations on an image classification task and hardware experiments on a continual learning problem with a custom 20,000-device prototyping platform show significant performance gains, outperforming prior methods at similar redundancy levels and overheads. For the image classification task with 20% stuck-at faults, accuracy improves from 40% to 89.6% (within 5% of baseline), and for the continual learning problem, accuracy improves from 55% to 71% (within 1% of baseline). The proposed scheme is broadly applicable to accelerators based on a variety of different non-volatile device technologies.</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

Layer ensemble averaging for fault tolerance in memristive neural networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月1日

查看全文
  • Osama Yousuf,
  • Brian D. Hoskins,
  • Karthick Ramu,
  • Mitchell Fream,
  • William A. Borders,
  • Advait Madhavan,
  • Matthew W. Daniels,
  • Andrew Dienstfrey,
  • Jabez J. McClelland,
  • Martin Lueker-Boden,
  • Gina C. Adam

摘要

Artificial neural networks have advanced due to scaling dimensions, but conventional computing struggles with inefficiencies due to memory bottlenecks. In-memory computing architectures using memristor devices offer promise but face challenges due to hardware non-idealities. This work proposes layer ensemble averaging—a hardware-oriented fault tolerance scheme for improving inference performance of non-ideal memristive neural networks programmed with pre-trained solutions. Simulations on an image classification task and hardware experiments on a continual learning problem with a custom 20,000-device prototyping platform show significant performance gains, outperforming prior methods at similar redundancy levels and overheads. For the image classification task with 20% stuck-at faults, accuracy improves from 40% to 89.6% (within 5% of baseline), and for the continual learning problem, accuracy improves from 55% to 71% (within 1% of baseline). The proposed scheme is broadly applicable to accelerators based on a variety of different non-volatile device technologies.