ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
The state-of-the-art approaches employ approximate computing to reduce the energy consumption of DNN hardware. Approximate DNNs then require extensive retraining afterwards to recover from the accuracy loss caused by the use of approximate operations. However, retraining of complex DNNs does not scale well. In this paper, we demonstrate that efficient approximations can be introduced into the computational path of DNN accelerators while retraining can completely be avoided. ALWANN provides highly optimized implementations of DNNs for custom low-power accelerators in which the number of computing units is lower than the number of DNN layers. First, a fully trained DNN (e.g., in TensorFlow) is converted to operate with 8-bit weights and 8-bit multipliers in convolutional layers. A suitable approximate multiplier is then selected for each computing element from a library of approximate multipliers in such a way that (i) one approximate multiplier serves several layers, and (ii) the overall classification error and energy consumption are minimized. The optimizations including the multiplier selection problem are solved by means of a multiobjective optimization NSGA-II algorithm. In order to completely avoid the computationally expensive retraining of DNN, which is usually employed to improve the classification accuracy, we propose a simple weight updating scheme that compensates the inaccuracy introduced by employing approximate multipliers. The proposed approach is evaluated for two architectures of DNN accelerators with approximate multipliers from the open-source “EvoApprox” library, while executing three versions of ResNet on CIFAR-10. We report that the proposed approach saves 30% of energy needed for multiplication in convolutional layers of ResNet-50 while the accuracy is degraded by only 0.6% (0.9% for the ResNet-14). The proposed technique and approximate layers are available as an open-source extension of TensorFlow at https://github.com/ehw-fit/tf-approximate.
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.
Integrity signals
Registry
Cites
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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
In-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537 · cited 2×
“The state-ofthe-art Tensor Processor Unit (TPU) accelerator accomplishes a satisfactory accuracy with 8-bit integer operations.”
MethodDeep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks
Chen, Y.-H., Krishna, T., Emer, J. S., & Sze, V. (2017) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2016.2616357 · Cited by 3,247
Can FPGAs Beat GPUs in Accelerating Next-Generation Deep Neural Networks?
Nurvitadhi, E., Venkatesh, G., Sim, J., Marr, D., Huang, R., Ong Gee Hock, J., Liew, Y. T., Srivatsan, K., Moss, D., Subhaschandra, S., et al. (2017) · Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/3020078.3021740 · Cited by 467
Cited by
Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework ICCAD Special Session Paper
Shafique, M., Marchisio, A., Wicaksana Putra, R. V., & Hanif, M. A. (2021) · 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD) · doi:10.1109/iccad51958.2021.9643539 · Cited by 58
“Furthermore, to find the configurations that offer good accuracy-energy trade-offs, the ALWANN framework [43] performs a DSE with a multi-objective NSGA-II algorithm.”
MethodSelf-citationMargin-Maximization in Binarized Neural Networks for Optimizing Bit Error Tolerance
Buschjager, S., Chen, J.-J., Chen, K.-H., Gunzel, M., Hakert, C., Morik, K., Novkin, R., Pfahler, L., & Yayla, M. (2021) · 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE) · doi:10.23919/date51398.2021.9473918 · Cited by 22
Automated HW/SW co-design for edge AI: state, challenges and steps ahead
Bringmann, O., Ecker, W., Feldner, I., Frischknecht, A., Gerum, C., Hämäläinen, T., Hanif, M. A., Klaiber, M. J., Mueller-Gritschneder, D., Bernardo, P. P., et al. (2021) · Proceedings of the 2021 International Conference on Hardware/Software Codesign and System Synthesis · doi:10.1145/3478684.3479261 · Cited by 20
“Towards this, different types of approximations can be employed at the hardware level, e.g., memory approximation by reducing the supply voltage below the standard specification [24][22] or functional approximation of the computational units [34].”
MethodSelf-citation
Metadata
- Authors
- Mrazek, V., Vasicek, Z., Sekanina, L., Hanif, M. A., & Shafique, M.
- Venue
- 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
- Publisher
- IEEE
- Published
- 2019-11
- Pages
- 1-8
- OpenAlex
- W2958306322
- Cited by
- 128
- References
- 5
- FWCI
- 22.32
- 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: ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining. https://app.cochat.ai/papers/10.1109/iccad45719.2019.8942068
- The paper
- Mrazek, V., Vasicek, Z., Sekanina, L., Hanif, M. A., & Shafique, M. (2019). ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining. 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD). https://doi.org/10.1109/iccad45719.2019.8942068
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.