Imperial College London
Alternate

ProfessorChristos-SavvasBouganis

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor of Intelligent Digital Systems
 
 
 
//

Contact

 

+44 (0)20 7594 6144christos-savvas.bouganis Website

 
 
//

Location

 

904Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Rizakis:2018:10.1007/978-3-319-78890-6,
author = {Rizakis, M and Venieris, SI and Kouris, A and Bouganis, C-S},
doi = {10.1007/978-3-319-78890-6},
pages = {3--15},
publisher = {Springer},
title = {Approximate FPGA-based LSTMs under computation time constraints},
url = {http://dx.doi.org/10.1007/978-3-319-78890-6},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Recurrent Neural Networks, with the prominence of LongShort-Term Memory (LSTM) networks, have demonstrated state-of-the-art accuracy in several emerging Artificial Intelligence tasks. Neverthe-less, the highest performing LSTM models are becoming increasinglydemanding in terms of computational and memory load. At the sametime, emerging latency-sensitive applications including mobile robots andautonomous vehicles often operate under stringent computation timeconstraints. In this paper, we address the challenge of deploying com-putationally demanding LSTMs at a constrained time budget by intro-ducing an approximate computing scheme that combines iterative low-rank compression and pruning, along with a novel FPGA-based LSTMarchitecture. Combined in an end-to-end framework, the approximationmethod  parameters  are  optimised  and  the  architecture  is  configuredto address the problem of high-performance LSTM execution in time-constrained applications.  Quantitative evaluation  on a real-life imagecaptioning application indicates that the proposed system required up to6.5×less time to achieve the same application-level accuracy comparedto a baseline method, while achieving an average of 25×higher accuracyunder the same computation time constraints.
AU  - Rizakis,M
AU  - Venieris,SI
AU  - Kouris,A
AU  - Bouganis,C-S
DO  - 10.1007/978-3-319-78890-6
EP  - 15
PB  - Springer
PY  - 2018///
SN  - 0302-9743
SP  - 3
TI  - Approximate FPGA-based LSTMs under computation time constraints
UR  - http://dx.doi.org/10.1007/978-3-319-78890-6
UR  - http://arxiv.org/abs/1801.02190v1
UR  - https://doi.org/10.1007/978-3-319-78890-6
UR  - http://hdl.handle.net/10044/1/64139
ER  -
Download