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.

本文介绍了一种近似计算方案，结合迭代低秩压缩和剪枝以及一种新型 FPGA 基于的 LSTM 结构，以部署计算时间受限的应用程序为挑战，将其优化和配置成高性能的 LSTM 执行体系框架。在真实生活中的图像字幕应用的定量评估表明，该方法需要的时间比基准方法少达 6.5 倍，同时在相同的计算时间限制下，实现了平均 25 倍的应用级别精度。