Header

UZH-Logo

Maintenance Infos

EILE: Efficient Incremental Learning on the Edge


Chen, Xi; Gao, Chang; Delbruck, Tobi; Liu, Shih-Chii (2021). EILE: Efficient Incremental Learning on the Edge. In: Artificial Intelligence Circuits and Systems (AICAS) 2021, Washington DC, 6 June 2021 - 9 June 2021, IEEE.

Abstract

This paper proposes a fully-connected network training architecture called EILE targeting incremental learning on edge. By using a novel reconfigurable processing element (PE) architecture, EILE avoids explicit transposition of weight matrices required for backpropagation to preserve the same efficient memory access pattern for both the forward (FP) and backward propagation (BP) phases. Experimental results on a Zynq XC7Z100 FPGA with 64 PEs show that EILE achieves 19.2 GOp/s peak throughput and maintains nearly 100 % PE utilization efficiency for both FP and BP with batch sizes from 1 to 32. EILE's small on-chip memory footprint and scalability to match any available off-chip memory bandwidth makes it an attractive ASIC architecture for energy-constrained training.

Abstract

This paper proposes a fully-connected network training architecture called EILE targeting incremental learning on edge. By using a novel reconfigurable processing element (PE) architecture, EILE avoids explicit transposition of weight matrices required for backpropagation to preserve the same efficient memory access pattern for both the forward (FP) and backward propagation (BP) phases. Experimental results on a Zynq XC7Z100 FPGA with 64 PEs show that EILE achieves 19.2 GOp/s peak throughput and maintains nearly 100 % PE utilization efficiency for both FP and BP with batch sizes from 1 to 32. EILE's small on-chip memory footprint and scalability to match any available off-chip memory bandwidth makes it an attractive ASIC architecture for energy-constrained training.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

141 downloads since deposited on 20 Oct 2021
24 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Physical Sciences > Artificial Intelligence
Physical Sciences > Computer Networks and Communications
Physical Sciences > Computer Vision and Pattern Recognition
Physical Sciences > Hardware and Architecture
Physical Sciences > Electrical and Electronic Engineering
Language:English
Event End Date:9 June 2021
Deposited On:20 Oct 2021 12:43
Last Modified:27 Feb 2022 08:21
Publisher:IEEE
OA Status:Green
Publisher DOI:https://doi.org/10.1109/AICAS51828.2021.9458554
  • Content: Accepted Version
  • Language: English