CoChat

Big/little deep neural network for ultra low power inference

Park, Eunhyeok, Kim, Dongyoung, Kim, Soobeom, Kim, Yong-Deok, Kim, Gunhee, Yoon, Sungroh, Yoo, Sungjoo · 2015 · 2015 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

Deep neural networks (DNNs) have recently proved their effectiveness in complex data analyses such as object/speech recognition. As their applications are being expanded to mobile devices, their energy efficiencies are becoming critical. In this paper, we propose a novel concept called big/LITTLE DNN (BL-DNN) which significantly reduces energy consumption required for DNN execution at a negligible loss of inference accuracy. The BL-DNN consists of a little DNN (consuming low energy) and a full-fledged big DNN. In order to reduce energy consumption, the BL-DNN aims at avoiding the execution of the big DNN whenever possible. The key idea for this goal is to execute the little DNN first for inference (without big DNN execution) and simply use its result as the final inference result as long as the result is estimated to be accurate. On the other hand, if the result from the little DNN is not considered to be accurate, the big DNN is executed to give the final inference result. This approach reduces the total energy consumption by obtaining the inference result only with the little, energy-efficient DNN in most cases, while maintaining the similar level of inference accuracy through selectively utilizing the big DNN execution. We present design-time and runtime methods to control the execution of big DNN under a trade-off between energy consumption and inference accuracy. Experiments with state-of-the-art DNNs for ImageNet and MNIST show that our proposed BL-DNN can offer up to 5…

Overview

Integrity signals

Registry

Crossref · 10.1109/codesisss.2015.7331375

Cites

35 of 35 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 35 references

Research works printed but not linked: 2

  1. park, 2015, 93TOPS/W scalable deep learning/inference processor with tetra-parallel MIMD architecture for big-data applications, Proc Int l Solid-States Circuits Conf (ISSCC)
  2. 0, DDR3 SDRAM System-Power Calculator

Cited by

Metadata

Authors
Park, E., Kim, D., Kim, S., Kim, Y.-D., Kim, G., Yoon, S., & Yoo, S.
Affiliations
  • Seoul National University (KR)
  • Samsung (South Korea) (KR)
Venue
2015 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)
Publisher
IEEE
Published
2015-10
Pages
124-132
OpenAlex
W4243928383
Cited by
130
References
35
Citations by year
2026: 3 · 2025: 5 · 2024: 19 · 2023: 19 · 2022: 22 · 2021: 21 · 2020: 15 · 2019: 12 · 2018: 6 · 2017: 3 · 2016: 5
FWCI
1.90
Type
conference paper
Language
en
Open access
closed
Locations
  • International Conference on Hardware/Software Codesign and System Synthesis (publishedVersion)
  • Seoul National University Open Repository (Seoul National University) (submittedVersion)
  • International Conference on Hardware/Software Codesign and System Synthesis
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Low-power high-performance VLSI design
  • Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
Keywords
deep neural network inference, ultra-low power, energy efficiency, energy-accuracy trade-off, mobile devices, image classification, handwritten digit recognition

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.