DECO: Dynamic Energy-aware Compression and Optimization for In-Memory Neural Networks

Rebati Gaire, Sepehr Tabrizchi, Deniz Najafi, Shaahin Angizi, Arman Roohi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper introduces DECO, a framework that combines model compression and processing-in-memory (PIM) to improve the efficiency of neural networks on IoT devices. By integrating these technologies, DECO significantly reduces energy consumption and operational latency through optimized data movement and computation, demonstrating notable performance gains on CIFAR-10/100 datasets. The DECO learning framework significantly improved the performance of compressed network modules derived from MobileNetV1 and VGG16, with accuracy gains of 1.66 % and 0.41 %, respectively, on the intricate CIFAR-100 dataset. DECO outperforms the GPU implementation by a significant margin, demonstrating up to a two-order-of-magnitude increase in speed based on our experiment.

Original languageEnglish (US)
Title of host publication2024 IEEE 67th International Midwest Symposium on Circuits and Systems, MWSCAS 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1441-1445
Number of pages5
ISBN (Electronic)9798350387179
DOIs
StatePublished - 2024
Event67th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2024 - Springfield, United States
Duration: Aug 11 2024Aug 14 2024

Publication series

NameMidwest Symposium on Circuits and Systems
ISSN (Print)1548-3746

Conference

Conference67th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2024
Country/TerritoryUnited States
CitySpringfield
Period8/11/248/14/24

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Keywords

  • feature extraction
  • Model compression
  • processing in-memory

Fingerprint

Dive into the research topics of 'DECO: Dynamic Energy-aware Compression and Optimization for In-Memory Neural Networks'. Together they form a unique fingerprint.

Cite this