Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index.

Minerva: enabling low-power, highly-accurate deep neural network accelerators

Abstract

The continued success of Deep Neural Networks (DNNs) in classification tasks has sparked a trend of accelerating their execution with specialized hardware. While published designs easily give an order of magnitude improvement over general-purpose hardware, few look beyond an initial implementation. This paper presents Minerva, a highly automated co-design approach across the algorithm, architecture, and circuit levels to optimize DNN hardware accelerators. Compared to an established fixed-point accelerator baseline, we show that fine-grained, heterogeneous datatype optimization reduces power by 1.5×; aggressive, inline predication and pruning of small activity values further reduces power by 2.0×; and active hardware fault detection coupled with domain-aware error mitigation eliminates an additional 2.7× through lowering SRAM voltages. Across five datasets, these optimizations provide a collective average of 8.1× power reduction over an accelerator baseline without compromising DNN model accuracy. Minerva enables highly accurate, ultra-low power DNN accelerators (in the range of tens of milliwatts), making it feasible to deploy DNNs in power-constrained IoT and mobile devices.

Overview

Integrity signals

Registry

Crossref · 10.1145/3007787.3001165

Cites

68 of 68 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 68 references

Research works printed but not linked: 4

  1. 10.5555/2627435.2670313 · doi:10.5555/2627435.2670313
  2. "Keras : Theano-based deep learning library." http://keras.io , 2015 . "Keras: Theano-based deep learning library." http://keras.io, 2015.
  3. S. Han , J. Pool , J. Tran , and W. Dally , " Learning both weights and connections for efficient neural network," in Advances in Neural Information Processing Systems , pp. 1135 -- 1143 , 2015 . S. Han, J. Pool, J. Tran, and W. Dally, "Learning both weights and connections for efficient neural network," in Advances in Neural Information Processing Systems, pp. 1135--1143, 2015.
  4. A. L. Maas , A. Y. Hannun , and A. Y. Ng , " Rectifier nonlinearities improve neural network acoustic models," in ICML , vol. 30 , 2013 . A. L. Maas, A. Y. Hannun, and A. Y. Ng, "Rectifier nonlinearities improve neural network acoustic models," in ICML, vol. 30, 2013.

Cited by

See all 446

Metadata

Authors
Reagen, B., Whatmough, P., Adolf, R., Rama, S., Lee, H., Lee, S. K., Hernández-Lobato, J. M., Wei, G.-Y., & Brooks, D.
Affiliations
Harvard University (US)
Venue
ACM SIGARCH Computer Architecture News
Published
2016-06-18
Volume
44
Issue
3
Pages
267-278
ISSN
0163-5964 (ISSN-L)
OpenAlex
W2513554817
Cited by
446
References
68
Citations by year
2026: 1 · 2025: 16 · 2024: 14 · 2023: 22 · 2022: 26 · 2021: 67 · 2020: 84 · 2019: 77 · 2018: 74 · 2017: 55 · 2016: 9
FWCI
33.01
Type
journal article
Language
en
Open access
closed
Locations
ACM SIGARCH Computer Architecture News (publishedVersion)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Low-power high-performance VLSI design
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
Keywords
deep neural network accelerators, energy consumption reduction, heterogeneous data types, hardware fault detection, error mitigation, energy-efficient computing, IoT devices, mobile devices

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: Minerva: enabling low-power, highly-accurate deep neural network accelerators. https://app.cochat.ai/papers/10.1145/3007787.3001165
The paper
Reagen, B., Whatmough, P., Adolf, R., Rama, S., Lee, H., Lee, S. K., Hernández-Lobato, J. M., Wei, G.-Y., & Brooks, D. (2016). Minerva: enabling low-power, highly-accurate deep neural network accelerators. ACM SIGARCH Computer Architecture News. https://doi.org/10.1145/3007787.3001165

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.