[논문]MixedNet: Network Design Strategies for Cost-Effective Quantized CNNs

Chang, Dong-Jin; Nam, Byeong-Gyu; Ryu, Seung-Tak

doi:10.1109/access.2021.3106658

[해외논문] MixedNet: Network Design Strategies for Cost-Effective Quantized CNNs 원문보기

IEEE access : practical research, open solutions, v.9, 2021년, pp.117554 - 117564

Chang, Dong-Jin (Korea Advanced Institute of Science and Technology, School of Electrical Engineering, Daejeon, South Korea) , Nam, Byeong-Gyu (Chungnam National University, Daejeon, South Korea) , Ryu, Seung-Tak (Korea Advanced Institute of Science and Technology, School of Electrical Engineering, Daejeon, South Korea)

Abstract ▼ AI-Helper

This paper proposes design strategies for a low-cost quantized neural network. To prevent the classification accuracy from being degraded by quantization, a structure-design strategy that utilizes a large number of channels rather than deep layers is proposed. In addition, a squeeze-and-excitation (SE) layer is adopted to enhance the performance of the quantized network. Through a quantitative analysis and simulations of the quantized key convolution layers of ResNet and MobileNets, a low-cost layer-design strategy for use when building a neural network is proposed. With this strategy, a low-cost network referred to as a MixedNet is constructed. A 4-bit quantized MixedNet example achieves an on-chip memory size reduction of 60% and fewer memory access by 53% with negligible classification accuracy degradation in comparison with conventional networks while also showing classification accuracy rates of approximately 73% for Cifar-100 and 93% for Cifar-10.

참고문헌 (28)

Zhang, Jintao, Wang, Zhuo, Verma, Naveen. In-Memory Computation of a Machine-Learning Classifier in a Standard 6T SRAM Array. IEEE journal of solid-state circuits, vol.52, no.4, 915-924.

상세보기
IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers 14.3 A 65nm computing-in-memory-based CNN processor with 2.9-to-35.8TOPS/W system energy efficiency using dynamic-sparsity performance-scaling architecture and energy-efficient Inter/Intra-macro data reuse yue 2020 234
IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers 14.2 A 65nm $24.7~\mu\text{J}$ /Frame 12.3 mW activation-similarity-aware convolutional neural network video processor using hybrid precision, inter-frame data reuse and mixed-bit-width difference-frame data codec yuan 2020 232
Hu, Jie, Shen, Li, Albanie, Samuel, Sun, Gang, Wu, Enhua. Squeeze-and-Excitation Networks. IEEE transactions on pattern analysis and machine intelligence, vol.42, no.8, 2011-2023.

상세보기
arXiv 1704 04861 MobileNets: Efficient convolutional neural networks for mobile vision applications howard 2017
10.1109/CVPR.2018.00474
IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers 14.1 A 510nW 0.41 V low-memory low-computation keyword-spotting chip using serial FFT-based MFCC and binarized depthwise separable convolutional neural network in 28nm CMOS shan 2020 230
arXiv 1905 11946 EfficientNet: Rethinking model scaling for convolutional neural networks tan 2019
arXiv 1611 01578 Neural architecture search with reinforcement learning zoph 2016
arXiv 1812 09818 Precision highway for ultra low-precision quantization park 2018
arXiv 1409 1556 Very deep convolutional networks for large-scale image recognition simonyan 2014
arXiv 1512 03385 Deep residual learning for image recognition he 2015
Kanda, K., Sadaaki, H., Sakurai, T.. 90% Write Power-Saving SRAM Using Sense-Amplifying Memory Cell. IEEE journal of solid-state circuits, vol.39, no.6, 927-933.

상세보기
arXiv 1602 02830 [cs] Binarized neural networks: Training neural networks with weights and activations constrained to +1 or -1 courbariaux 2016
10.1109/ISCAS.2019.8702698
10.1109/ISSCC.2017.7870350
Bankman, Daniel, Yang, Lita, Moons, Bert, Verhelst, Marian, Murmann, Boris. An Always-On 3.8 $\mu$J/86% CIFAR-10 Mixed-Signal Binary CNN Processor With All Memory on Chip in 28-nm CMOS. IEEE journal of solid-state circuits, vol.54, no.1, 158-172.

상세보기
Chang, Dong-Jin, Nam, Byeong-Gyu, Ryu, Seung-Tak. Compact Mixed-Signal Convolutional Neural Network Using a Single Modular Neuron. IEEE transactions on circuits and systems. a publication of the IEEE Circuits and Systems Society. I, Regular papers, vol.67, no.12, 5189-5199.

상세보기
Proc Adv Neural Inf Process Syst (NIPS) ImageNet classification with deep convolutional neural networks krizhevsky 2012 25 1097
10.1109/VLSIC.2018.8502421
Nature Deep learning lecun 2015 10.1038/nature14539 521 436

상세보기
Jiang, Feibo, Wang, Kezhi, Dong, Li, Pan, Cunhua, Xu, Wei, Yang, Kun. Deep-Learning-Based Joint Resource Scheduling Algorithms for Hybrid MEC Networks. IEEE Internet of things journal : a joint publication of the IEEE Sensors Council, the IEEE Communications Society, the IEEE Computer Society, the IEEE Signal Processing Society, vol.7, no.7, 6252-6265.

상세보기
Proc 34th Int Conf Mach Learn Analytical guarantees on numerical precision of deep neural networks sakr 2017 70 3007
Jiang, Feibo, Wang, Kezhi, Dong, Li, Pan, Cunhua, Xu, Wei, Yang, Kun. AI Driven Heterogeneous MEC System with UAV Assistance for Dynamic Environment: Challenges and Solutions. IEEE network, vol.35, no.1, 400-408.

상세보기
arXiv 2003 13630 TResNet: High performance GPU-dedicated architecture ridnik 2020
arXiv 1912 11370 Big transfer (BiT): General visual representation learning kolesnikov 2019
IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers 15.5 A 28nm 64Kb 6T SRAM computing-in-memory macro with 8b MAC operation for AI edge chips si 2020 246
arXiv 1606 06160 [cs] DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients zhou 2016

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 보기

AccessON 원문보기

원문 URL 링크

DOI : 10.1109/ACCESS.2021.3106658 [무료]
IEEE : 저널 > 논문 [무료]
AccessON : 저널

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

오픈액세스(OA) 유형

GOLD

오픈액세스 학술지에 출판된 논문

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증