Approximate FPGA-based LSTMs under Computation Time Constraints
Abstract
Recurrent Neural Networks and in particular Long Short-Term Memory (LSTM) networks have demonstrated state-of-the-art accuracy in several emerging Artificial Intelligence tasks. However, the models are becoming increasingly demanding in terms of computational and memory load. Emerging latency-sensitive applications including mobile robots and autonomous vehicles often operate under stringent computation time constraints. In this paper, we address the challenge of deploying computationally demanding LSTMs at a constrained time budget by introducing an approximate computing scheme that combines iterative low-rank compression and pruning, along with a novel FPGA-based LSTM architecture. Combined in an end-to-end framework, the approximation method's parameters are optimised and the architecture is configured to address the problem of high-performance LSTM execution in time-constrained applications. Quantitative evaluation on a real-life image captioning application indicates that the proposed methods required up to 6.5x less time to achieve the same application-level accuracy compared to a baseline method, while achieving an average of 25x higher accuracy under the same computation time constraints.
Cite
@article{arxiv.1801.02190,
title = {Approximate FPGA-based LSTMs under Computation Time Constraints},
author = {Michalis Rizakis and Stylianos I. Venieris and Alexandros Kouris and Christos-Savvas Bouganis},
journal= {arXiv preprint arXiv:1801.02190},
year = {2018}
}
Comments
Accepted at the 14th International Symposium in Applied Reconfigurable Computing (ARC) 2018