Algorithm/Accelerator Co-Design and Co-Search for Edge AI

Xiaofan Zhang, Yuhong Li, Junhao Pan, Deming Chen

Research output: Contribution to journalArticlepeer-review


The world has seen the great success of deep neural networks (DNNs) in a massive number of artificial intelligence (AI) applications. However, developing high-quality AI services to satisfy diverse real-life edge scenarios still encounters many difficulties. As DNNs become more compute-and memory-intensive, it is challenging for edge devices to accommodate them with limited computation/memory resources, tight power budgets, and small form-factors. Challenges also come from the demanding requirements of edge AI, requesting real-time responses, high-throughput performance, and reliable inference accuracy. To address these challenges, we propose a series of efficient design methods to perform algorithm/accelerator co-design and co-search for optimized edge AI solutions. We demonstrate our proposed methods on popular edge AI applications (object detection and image classification) and achieve significant improvements than prior designs.

Original languageEnglish (US)
Pages (from-to)3064-3070
Number of pages7
JournalIEEE Transactions on Circuits and Systems II: Express Briefs
Issue number7
StatePublished - Jul 1 2022


  • AI accelerators
  • Deep neural network
  • Edge computing
  • HW/SW co-design

ASJC Scopus subject areas

  • Electrical and Electronic Engineering


Dive into the research topics of 'Algorithm/Accelerator Co-Design and Co-Search for Edge AI'. Together they form a unique fingerprint.

Cite this