DECO: Dynamic Energy-aware Compression and Optimization for In-Memory Neural Networks
Document Type
Conference Proceeding
Publication Date
1-1-2024
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.
Identifier
85205027821 (Scopus)
ISBN
[9798350387179]
Publication Title
Midwest Symposium on Circuits and Systems
External Full Text Location
https://doi.org/10.1109/MWSCAS60917.2024.10658771
ISSN
15483746
First Page
1441
Last Page
1445
Grant
2216772
Fund Ref
National Science Foundation
Recommended Citation
Gaire, Rebati; Tabrizchi, Sepehr; Najafi, Deniz; Angizi, Shaahin; and Roohi, Arman, "DECO: Dynamic Energy-aware Compression and Optimization for In-Memory Neural Networks" (2024). Faculty Publications. 865.
https://digitalcommons.njit.edu/fac_pubs/865