CoChat

Scalable high-performance architecture for convolutional ternary neural networks on FPGA

Open access
Prost-Boucle, Adrien, Bourge, Alban, Petrot, Frederic, Alemdar, Hande, Caldwell, Nicholas, Leroy, Vincent · 2017 · 2017 27th International Conference on Field Programmable Logic and Applications (FPL)
Cited by 78

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Abstract

Thanks to their excellent performances on typical artificial intelligence problems, deep neural networks have drawn a lot of interest lately. However, this comes at the cost of large computational needs and high power consumption. Benefiting from high precision at acceptable hardware cost on these difficult problems is a challenge. To address it, we advocate the use of ternary neural networks (TNN) that, when properly trained, can reach results close to the state of the art using floatingpoint arithmetic. We present a highly versatile FPGA friendly architecture for TNN in which we can vary both the number of bits of the input data and the level of parallelism at synthesis time, allowing to trade throughput for hardware resources and power consumption. To demonstrate the efficiency of our proposal, we implement high-complexity convolutional neural networks on the Xilinx Virtex-7 VC709 FPGA board. While reaching a better accuracy than comparable designs, we can target either high throughput or low power. We measure a throughput up to 27 000 fps at ≈7W or up to 8.36 TMAC/s at ≈13 W.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.23919/fpl.2017.8056850

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 5 references

Research works printed but not linked: 17

  1. 10.1109/IJCNN.2017.7966166 · DOI · Paper page
  2. 10.1109/ISVLSI.2016.111 · DOI · Paper page
  3. 10.1016/0893-6080(88)90203-1 · doi:10.1016/0893-6080(88)90203-1
  4. 10.1109/ICMEL.1995.500978 · doi:10.1109/icmel.1995.500978
  5. p ?koda, 2011, Implementation Framework for Artificial Neural Networks on FPGA, 2011 Proceedings of the 34th International Convention MIPRO, 274
  6. 10.1145/2815631 · doi:10.1145/2815631
  7. krizhevsky, 2009, Learning multiple layers of features from tiny images, University of Toronto Technical Report
  8. stallkamp, 2011, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, International Joint Conference on Neural Networks
  9. esser, 2015, Backpropagation for energy-efficient neuromorphic computing, Advances in neural information processing systems, 1117
  10. 10.23919/DATE.2017.7927280 · DOI
  11. courbariaux, 2015, Binaryconnect: Training deep neural networks with binary weights during propagations, Advances in neural information processing systems, 3123
  12. asanovic, 1991, Experimental determination of precision requirements for back-propagation training of artificial neural networks, Proceedings 2nd International Conference on Microelectronics for Neural Networks
  13. 10.1109/ISCAS.2010.5537908 · DOI · Paper page
  14. 10.1145/1815961.1816008 · doi:10.1145/1815961.1816008
  15. netzer, 2011, Reading digits in natural images with unsupervised feature learning, NIPS Workshop on Deep Learning and Unsupervised Feature Learning
  16. zhao, 2017, Accelerating binarized convolutional neural networks with software-programmable fpgas, Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, 15, 10.1145/3020078.3021741 · DOI · Paper page
  17. li, 2017, A 7 663-tops 8 2-w energy-efficient fpga accelerator for binary convolutional neural networks

Cited by

See all 78

Metadata

Authors
Prost-Boucle, A., Bourge, A., Petrot, F., Alemdar, H., Caldwell, N., & Leroy, V.
Venue
2017 27th International Conference on Field Programmable Logic and Applications (FPL)
Publisher
IEEE
Published
2017-09
Pages
1-7
OpenAlex
W2762597430
Cited by
78
References
5
FWCI
3.40
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Scalable high-performance architecture for convolutional ternary neural networks on FPGA. https://app.cochat.ai/papers/10.23919/fpl.2017.8056850
The paper
Prost-Boucle, A., Bourge, A., Petrot, F., Alemdar, H., Caldwell, N., & Leroy, V. (2017). Scalable high-performance architecture for convolutional ternary neural networks on FPGA. 2017 27th International Conference on Field Programmable Logic and Applications (FPL). https://doi.org/10.23919/fpl.2017.8056850

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.