연구동향 분석
박사

ClassRBM Hardware for On-Device Semi-Supervised Learning with Spin-based Memristor Device = 스핀 멤리스터 소자 기반 온디바이스 반지도학습이 가능한 추론을 위한 제한된 볼츠만 머신 하드웨어 구현

이우석 2020년

논문상세정보
인용/피인용
' ClassRBM Hardware for On-Device Semi-Supervised Learning with Spin-based Memristor Device = 스핀 멤리스터 소자 기반 온디바이스 반지도학습이 가능한 추론을 위한 제한된 볼츠만 머신 하드웨어 구현' 의 주제별 논문영향력
논문영향력 선정 방법
논문영향력 요약
주제
  • ClassRBM
  • Embedded system
  • Neural network
  • Neuromorphic hardware
  • on-device learning
  • semi-supervised learning
동일주제 총논문수 논문피인용 총횟수 주제별 논문영향력의 평균
217 0

0.0%

' ClassRBM Hardware for On-Device Semi-Supervised Learning with Spin-based Memristor Device = 스핀 멤리스터 소자 기반 온디바이스 반지도학습이 가능한 추론을 위한 제한된 볼츠만 머신 하드웨어 구현' 의 참고문헌

  • per neuron weight rbm processor supporting on-chip learning/inference for iot applications
    52 ( 10 ) :2601–2612 [2017]
  • [9] Chih-Cheng Chang, Ming-Hung Wu, Jia-Wei Lin, Chun-Hsien Li, Vivek Parmar, Heng-Yuan Lee, Jeng-Hua Wei, Shyh-Shyuan Sheu, Manan Suri, Tian-Sheuan Chang, et al. Nv-bnn: An accurate deep convolutional neural network based on binary stt-mram for adaptive ai edge. In Proceedings of the 56th Annual Design Automation Conference 2019, page 30. ACM, 2019.
  • [49] Tetsuo Endoh and Hiroaki Honjo. A recent progress of spintronics devices for integrated circuit applications. Journal of Low Power Electronics and Applications, 8(4):44, 2018.
  • [47] Koji Ando, Shinobu Fujita, Masanori Hayashikoshi, and Yoshikazu Fujimori. Non-volatile memories. In Normally-OffComputing, pages 27–55. Springer, 2017.
    [2017]
  • Why does unsupervised pre-training help deep learning ? JMLR
    11 ( Feb ) :625–660 [2010]
  • Vision as bayesian inference : analysis by synthesis ?
    10 ( 7 ) :301–308 [2006]
  • Using memristors for robust local learning of hardware restricted boltzmann machines
    9 ( 1 ) :1851 [2019]
  • Ultra low power associative computing with spin neurons and resistive crossbar memory
    [2013]
  • Treereweighted belief propagation algorithms and approximate ml estimation by pseudo-moment matching
    [2003]
  • Training products of experts by minimizing contrastive divergence
    14 ( 8 ) :1771–1800 [2002]
  • The benefits of noise in neural systems : bridging theory and experiment
    12 ( 7 ) :415 [2011]
  • Stochastic inference and learning enabled by magnetic tunnel junctions .
    [2018]
  • Stochastic dynamics as a principle of brain function
    88 ( 1 ) :1–16 [2009]
  • Statistical analysis of non-lattice data
    24 ( 3 ) :179–195 [1975]
  • Spin-transfer torque mram ( stt-mram ) :Challenges and prospects
    18 ( 6 ) :33–40 [2008]
  • Spin-transfer torque magnetic neuron for low power neuromorphicComputing
    [2015]
  • Spin-transfer torque magnetic memory as a stochastic memristive synapse for neuromorphic systems .
    9 ( 2 ) :166–174 [2015]
  • Spin-torque devices with hard axis initialization as stochastic binary neurons .
    8 ( 1 ) :16689 [2018]
  • Restricted boltzmann machines forCollaborative filtering
    [2007]
  • Resource efficient arithmetic effects on rbm neural network solution quality using mnist
    [2011]
  • Regularization of neural networks using dropconnect
    pages 1058–1066 [2013]
  • Reducing the dimensionality of data with neural networks
    313 ( 5786 ) :504–507 [2006]
  • Programmable synaptic metaplasticity and below femtojoule spiking energy realized in graphene-based neuromorphic memristor .
    10 ( 24 ) :20237– 20243 [2018]
  • Probabilistic machine learning and artificial intelligence
    [2015]
  • Probabilistic deep spiking neural systems enabled by magnetic tunnel junction .
    63 ( 7 ) :2963–2970 , [2016]
  • Principled hybrids of generative and discriminative models .
    volume 1 , pages 87–94 [2006]
  • Parametric inference for imperfectly observed gibbsian fields
    82 ( 4 ) :625–645 [1989]
  • Organic core-sheath nanowire artificial synapses with femtojoule energy consumption
    2 ( 6 ) : e1501326 [2016]
  • On discriminative vs. generative classifiers : A comparison of logistic regression and naive bayes
    [2002]
  • Nonvolatile circuits-devices interaction for memory , logic and artificial intelligence
    [2018]
  • Multi-column deep neural networks for image classification
    [2012]
  • Mram as embedded non-volatile memory solution for 22ffl finfet technology .
    [2018]
  • Learning algorithms for the classification restricted boltzmann machine .
    13 ( Mar ) :643–669 [2012]
  • Inductive principles for restricted boltzmann machine learning
    pages 509–516 [2010]
  • Improving semi-supervised learning with auxiliary deep generative models
    [2015]
  • Hybrid deep learning for face verification
    38 ( 10 ) :1997–2009 [2016]
  • Humanlevel concept learning through probabilistic program induction
    [2015]
  • Hardware implementation of a real-time neural network controller with a dsp and an fpga for nonlinear systems
    54 ( 1 ) :265–271 [2007]
  • Graph regularized restricted boltzmann machine
    [2017]
  • Generating facial expressions with deep belief nets
    [2008]
  • Geco : classification restricted boltzmann machine hardware for on-chip learning
    [2017]
  • Geco : Classification restricted boltzmann machine hardware for on-chip semisupervised learning and bayesian inference .
    [2019]
  • Fully parallel on-chip learning hardware neural network for real-time control
    volume 5 , pages 371–374 [1999]
  • Facing the reality of data stream classification : coping with scarcity of labeled data
    33 ( 1 ) :213–244 [2012]
  • Eventdriven contrastive divergence for spiking neuromorphic systems .
    [2012]
  • Error tolerance analysis of deep learning hardware using a restricted boltzmann machine toward low-power memory implementation
    64 ( 4 ) :462–466 [2017]
  • Emerging memory technologies : Recent trends and prospects
    8 ( 2 ) :43–56 [2016]
  • Embedded stt-mram in 28-nm fdsoi logic process for industrial mcu/iot application
    [2018]
  • Embedded streaming deep neural networks accelerator with applications .
    28 ( 7 ) :1572– 1583 [2017]
  • Electrical modeling of stochastic spin transfer torque writing in magnetic tunnel junctions for memory and logic applications
    49 ( 7 ) :4375–4378 [2013]
  • Efficient embedded neural-network-based license plate recognition system
    57 ( 5 ) :2675–2683 [2008]
  • Discriminative feature extraction with deep neural networks
    pages 1–8 [2010]
  • Detecting breathing rates and depth of breath using lpcs and restricted boltzmann machines
    [2019]
  • Demonstration of highly manufacturable stt-mram embedded in 28nm logic .
    [2018]
  • Deepx : Deep learning accelerator for restricted boltzmann machine artificial neural networks .
    [2017]
  • Deep boltzmann machine based condition prediction for smart manufacturing
    10 ( 3 ) :851–861 [2019]
  • Compact model of magnetic tunnel junction with stochastic spin transfer torque switching for reliability analyses
    54 ( 9-10 ) :1774–1778 [2014]
  • An energy-efficient and scalable deep learning/inference processor with tetra-parallel mimd architecture for big data applications .
    9 ( 6 ) :838–848 , [2015]
  • An all-memristor deep spiking neural computing system : A step toward realizing the low-power stochastic brain
    2 ( 5 ) :345–358 [2018]
  • A two-terminal perpendicular spintransfer torque based artificial neuron
    51 ( 50 ) :504002 [2018]
  • A review of emerging non-volatile memory ( NVM ) technologies and applications
    [2016]
  • A fully pipelined fpga architecture of a factored restricted boltzmann machine artificial neural network .
    7 ( 1 ) :5 , [2014]
  • A Fast Learning Algorithm for Deep Belief Nets
    18 ( 7 ) :1527–1554 [2006]
  • A 0.086-mmˆ212.7-pj/sop 64k-synapse 256-neuron online-learning digital spiking neuromorphic processor in 28-nm cmos
    13 ( 1 ) :145–158 [2018]
  • 93tops/w scalable deep learning/inference processor with tetra-parallel mimd architecture for big-data applications .
    [2015]
  • 22-nm fd-soi embedded mram technology for low-power automotive-grade-l mcu applications .
    [2018]