RECORD
Approximate FPGA-based LSTMs under Computation Time Constraints
Computer Vision and Pattern Recognition · Submitted 7 Jan 2018
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim 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.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | 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. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | However, the models are becoming increasingly demanding in terms of computational and memory load. | background 0.95 | 0.06 | 0.01 | asserted 0.99 |
| s2 | Emerging latency-sensitive applications including mobile robots and autonomous vehicles often operate under stringent computation time constraints. | background 0.99 | 0.05 | 0.02 | asserted 0.99 |
| s3 | 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. | contribution 0.98 | 0.93 | 0.10 | asserted 0.99 |
| s4 | 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. | method 0.87 | 0.87 | 0.06 | asserted 0.99 |
| s5 | 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. | result 1.00 | 0.95 | 0.88 | hedged possibility 0.66 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.