Scholarlink

<p>Spatial-temporal information perception is widely used for motion processing in dynamic scenes, but present technology requires relatively huge hardware resource consumption. The attention mechanism helps the human brain extract required information from tremendous data at a low cost. Here, we propose an attention-inspired artificial intelligence architecture based on hetero-dimensional modulations between zero-dimensional contact and two-dimensional electrostatic interfaces. An adaptive spatial-temporal information processing primitive is successfully implemented based on in-memory analog computing. Experiments of attention adjustments responding to different situations validate the adaptation capability to environmental changes. A demonstration of 5×5-unit data stream processing is conducted, and intensities of spatial and temporal information are varied with attention distribution from 0% to 100%. The attention-inspired device is applied to autonomous driving edge intelligence scenarios, showing high adaptability to traffic scene variations. The proposed architecture exhibits a tens-fold latency reduction, hundreds-fold area improvement, and thousands-fold energy saving compared to the conventional transistor-based circuit.</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

Adaptive spatial-temporal information processing based on in-memory attention-inspired devices

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月12日

查看全文
  • Jiong Pan,
  • Fan Wu,
  • Kangan Qian,
  • Kun Jiang,
  • Yanming Liu,
  • Zeda Wang,
  • Pengwen Guo,
  • Jiaju Yin,
  • Diange Yang,
  • He Tian,
  • Yi Yang,
  • Tian-Ling Ren

摘要

Spatial-temporal information perception is widely used for motion processing in dynamic scenes, but present technology requires relatively huge hardware resource consumption. The attention mechanism helps the human brain extract required information from tremendous data at a low cost. Here, we propose an attention-inspired artificial intelligence architecture based on hetero-dimensional modulations between zero-dimensional contact and two-dimensional electrostatic interfaces. An adaptive spatial-temporal information processing primitive is successfully implemented based on in-memory analog computing. Experiments of attention adjustments responding to different situations validate the adaptation capability to environmental changes. A demonstration of 5×5-unit data stream processing is conducted, and intensities of spatial and temporal information are varied with attention distribution from 0% to 100%. The attention-inspired device is applied to autonomous driving edge intelligence scenarios, showing high adaptability to traffic scene variations. The proposed architecture exhibits a tens-fold latency reduction, hundreds-fold area improvement, and thousands-fold energy saving compared to the conventional transistor-based circuit.