CoChat

A Reconfigurable Streaming Deep Convolutional Neural Network Accelerator for Internet of Things

Open access
Du, Li, Du, Yuan, Li, Yilei, Su, Junjie, Kuan, Yen-Cheng, Liu, Chun-Chen, Chang, Mau-Chung Frank · 2018 · IEEE Transactions on Circuits and Systems I: Regular Papers

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

Convolutional neural network (CNN) offers significant accuracy in image detection. To implement image detection using CNN in the Internet of Things (IoT) devices, a streaming hardware accelerator is proposed. The proposed accelerator optimizes the energy efficiency by avoiding unnecessary data movement. With unique filter decomposition technique, the accelerator can support arbitrary convolution window size. In addition, max-pooling function can be computed in parallel with convolution by using separate pooling unit, thus achieving throughput improvement. A prototype accelerator was implemented in TSMC 65-nm technology with a core size of 5 mm2. The accelerator can support major CNNs and achieve 152GOPS peak throughput and 434GOPS/W energy efficiency at 350 mW, making it a promising hardware accelerator for intelligent IoT devices.

Overview

Integrity signals

Registry

Crossref · 10.1109/tcsi.2017.2735490

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 16 references

Research works printed but not linked: 5

  1. zeng, 2015, Traffic sign recognition using extreme learning classifier with deep convolution features, Proc Int Conf Intell Sci Big Data Eng, 1
  2. krizhevsky, 2012, ImageNet classification with deep convolution neural networks, Proc Conf Workshop Neural Inf Process Syst, 1106
  3. bilac, 2016, How to Classify Images With TensorFlow Using Google Cloud Machine Learning and Cloud Dataflow
  4. 2016, Amazon Rekognition
  5. 2017, Hardware IP Demo

Cited by

Items 101–200 of 223

Metadata

Authors
Du, L., Du, Y., Li, Y., Su, J., Kuan, Y.-C., Liu, C.-C., & Chang, M.-C. F.
Affiliations
  • University of California, Los Angeles (US)
  • National Yang Ming Chiao Tung University (TW)
Venue
IEEE Transactions on Circuits and Systems I: Regular Papers
Published
2018-01
Volume
65
Issue
1
Pages
198-208
ISSN
  • 1549-8328 (ISSN-L)
  • 1558-0806
OpenAlex
W2734572653
Cited by
205
References
15
Citations by year
2026: 6 · 2025: 9 · 2024: 22 · 2023: 23 · 2022: 31 · 2021: 37 · 2020: 34 · 2019: 24 · 2018: 19
FWCI
8.74
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Circuits and Systems I Regular Papers (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
U.S. Department of Commerce
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
Keywords
convolutional neural network accelerator, Internet of Things, reconfigurable accelerators, filter decomposition, energy efficiency, image detection, 65 nm CMOS

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

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.