IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v13y2022i1d10.1038_s41467-022-30305-8.html
   My bibliography  Save this article

Neural sampling machine with stochastic synapse allows brain-like learning and inference

Author

Listed:
  • Sourav Dutta

    (University of Notre Dame)

  • Georgios Detorakis

    (University of California Irvine)

  • Abhishek Khanna

    (University of Notre Dame)

  • Benjamin Grisafe

    (University of Notre Dame)

  • Emre Neftci

    (University of California Irvine)

  • Suman Datta

    (University of Notre Dame)

Abstract

Many real-world mission-critical applications require continual online learning from noisy data and real-time decision making with a defined confidence level. Brain-inspired probabilistic models of neural network can explicitly handle the uncertainty in data and allow adaptive learning on the fly. However, their implementation in a compact, low-power hardware remains a challenge. In this work, we introduce a novel hardware fabric that can implement a new class of stochastic neural network called Neural Sampling Machine (NSM) by exploiting the stochasticity in the synaptic connections for approximate Bayesian inference. We experimentally demonstrate an in silico hybrid stochastic synapse by pairing a ferroelectric field-effect transistor (FeFET)-based analog weight cell with a two-terminal stochastic selector element. We show that the stochastic switching characteristic of the selector between the insulator and the metallic states resembles the multiplicative synaptic noise of the NSM. We perform network-level simulations to highlight the salient features offered by the stochastic NSM such as performing autonomous weight normalization for continual online learning and Bayesian inferencing. We show that the stochastic NSM can not only perform highly accurate image classification with 98.25% accuracy on standard MNIST dataset, but also estimate the uncertainty in prediction (measured in terms of the entropy of prediction) when the digits of the MNIST dataset are rotated. Building such a probabilistic hardware platform that can support neuroscience inspired models can enhance the learning and inference capability of the current artificial intelligence (AI).

Suggested Citation

  • Sourav Dutta & Georgios Detorakis & Abhishek Khanna & Benjamin Grisafe & Emre Neftci & Suman Datta, 2022. "Neural sampling machine with stochastic synapse allows brain-like learning and inference," Nature Communications, Nature, vol. 13(1), pages 1-10, December.
  • Handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-30305-8
    DOI: 10.1038/s41467-022-30305-8
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-022-30305-8
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-022-30305-8?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Stefano Ambrogio & Pritish Narayanan & Hsinyu Tsai & Robert M. Shelby & Irem Boybat & Carmelo Nolfo & Severin Sidler & Massimo Giordano & Martina Bodini & Nathan C. P. Farinha & Benjamin Killeen & Chr, 2018. "Equivalent-accuracy accelerated neural-network training using analogue memory," Nature, Nature, vol. 558(7708), pages 60-67, June.
    2. Sourav Dutta & Abhinav Parihar & Abhishek Khanna & Jorge Gomez & Wriddhi Chakraborty & Matthew Jerry & Benjamin Grisafe & Arijit Raychowdhury & Suman Datta, 2019. "Programmable coupled oscillators for synchronized locomotion," Nature Communications, Nature, vol. 10(1), pages 1-10, December.
    3. Lars Buesing & Johannes Bill & Bernhard Nessler & Wolfgang Maass, 2011. "Neural Dynamics as Sampling: A Model for Stochastic Computation in Recurrent Networks of Spiking Neurons," PLOS Computational Biology, Public Library of Science, vol. 7(11), pages 1-22, November.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Liuting Shan & Qizhen Chen & Rengjian Yu & Changsong Gao & Lujian Liu & Tailiang Guo & Huipeng Chen, 2023. "A sensory memory processing system with multi-wavelength synaptic-polychromatic light emission for multi-modal information recognition," Nature Communications, Nature, vol. 14(1), pages 1-11, December.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Peng Chen & Fenghao Liu & Peng Lin & Peihong Li & Yu Xiao & Bihua Zhang & Gang Pan, 2023. "Open-loop analog programmable electrochemical memory array," Nature Communications, Nature, vol. 14(1), pages 1-9, December.
    2. Djohan Bonnet & Tifenn Hirtzlin & Atreya Majumdar & Thomas Dalgaty & Eduardo Esmanhotto & Valentina Meli & Niccolo Castellani & Simon Martin & Jean-François Nodin & Guillaume Bourgeois & Jean-Michel P, 2023. "Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    3. Simone D’Agostino & Filippo Moro & Tristan Torchet & Yiğit Demirağ & Laurent Grenouillet & Niccolò Castellani & Giacomo Indiveri & Elisa Vianello & Melika Payvand, 2024. "DenRAM: neuromorphic dendritic architecture with RRAM for efficient temporal processing with delays," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    4. Wen-Hao Zhang & Si Wu & Krešimir Josić & Brent Doiron, 2023. "Sampling-based Bayesian inference in recurrent circuits of stochastic spiking neurons," Nature Communications, Nature, vol. 14(1), pages 1-19, December.
    5. Yang Qi & Pulin Gong, 2022. "Fractional neural sampling as a theory of spatiotemporal probabilistic computations in neural circuits," Nature Communications, Nature, vol. 13(1), pages 1-19, December.
    6. Xiangjin Wu & Asir Intisar Khan & Hengyuan Lee & Chen-Feng Hsu & Huairuo Zhang & Heshan Yu & Neel Roy & Albert V. Davydov & Ichiro Takeuchi & Xinyu Bao & H.-S. Philip Wong & Eric Pop, 2024. "Novel nanocomposite-superlattices for low energy and high stability nanoscale phase-change memory," Nature Communications, Nature, vol. 15(1), pages 1-8, December.
    7. Ruibin Mao & Bo Wen & Arman Kazemi & Yahui Zhao & Ann Franchesca Laguna & Rui Lin & Ngai Wong & Michael Niemier & X. Sharon Hu & Xia Sheng & Catherine E. Graves & John Paul Strachan & Can Li, 2022. "Experimentally validated memristive memory augmented neural network with efficient hashing and similarity search," Nature Communications, Nature, vol. 13(1), pages 1-13, December.
    8. Lieder, Falk & Griffiths, Tom & Hsu, Ming, 2016. "Over-representation of extreme events in decision-making reflects rational use of cognitive resources," OSF Preprints kxxag, Center for Open Science.
    9. Bin Gao & Ying Zhou & Qingtian Zhang & Shuanglin Zhang & Peng Yao & Yue Xi & Qi Liu & Meiran Zhao & Wenqiang Zhang & Zhengwu Liu & Xinyi Li & Jianshi Tang & He Qian & Huaqiang Wu, 2022. "Memristor-based analogue computing for brain-inspired sound localization with in situ training," Nature Communications, Nature, vol. 13(1), pages 1-8, December.
    10. Chang Liu & Pek Jun Tiw & Teng Zhang & Yanghao Wang & Lei Cai & Rui Yuan & Zelun Pan & Wenshuo Yue & Yaoyu Tao & Yuchao Yang, 2024. "VO2 memristor-based frequency converter with in-situ synthesize and mix for wireless internet-of-things," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
    11. Melika Payvand & Filippo Moro & Kumiko Nomura & Thomas Dalgaty & Elisa Vianello & Yoshifumi Nishi & Giacomo Indiveri, 2022. "Self-organization of an inhomogeneous memristive hardware for sequence learning," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    12. Milad Shafiee & Guillaume Bellegarda & Auke Ijspeert, 2024. "Viability leads to the emergence of gait transitions in learning agile quadrupedal locomotion on challenging terrains," Nature Communications, Nature, vol. 15(1), pages 1-16, December.
    13. Ke Yang & Yanghao Wang & Pek Jun Tiw & Chaoming Wang & Xiaolong Zou & Rui Yuan & Chang Liu & Ge Li & Chen Ge & Si Wu & Teng Zhang & Ru Huang & Yuchao Yang, 2024. "High-order sensory processing nanocircuit based on coupled VO2 oscillators," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    14. Robert Legenstein & Wolfgang Maass, 2014. "Ensembles of Spiking Neurons with Noise Support Optimal Probabilistic Inference in a Dynamically Changing Environment," PLOS Computational Biology, Public Library of Science, vol. 10(10), pages 1-27, October.
    15. Darshit Mehta & Mustafizur Rahman & Kenji Aono & Shantanu Chakrabartty, 2022. "An adaptive synaptic array using Fowler–Nordheim dynamic analog memory," Nature Communications, Nature, vol. 13(1), pages 1-11, December.
    16. Dejan Pecevski & Lars Buesing & Wolfgang Maass, 2011. "Probabilistic Inference in General Graphical Models through Sampling in Stochastic Networks of Spiking Neurons," PLOS Computational Biology, Public Library of Science, vol. 7(12), pages 1-25, December.
    17. Maldonado, D. & Aguilera-Pedregosa, C. & Vinuesa, G. & García, H. & Dueñas, S. & Castán, H. & Aldana, S. & González, M.B. & Moreno, E. & Jiménez-Molinos, F. & Campabadal, F. & Roldán, J.B., 2022. "An experimental and simulation study of the role of thermal effects on variability in TiN/Ti/HfO2/W resistive switching nonlinear devices," Chaos, Solitons & Fractals, Elsevier, vol. 160(C).
    18. Fadi Jebali & Atreya Majumdar & Clément Turck & Kamel-Eddine Harabi & Mathieu-Coumba Faye & Eloi Muhr & Jean-Pierre Walder & Oleksandr Bilousov & Amadéo Michaud & Elisa Vianello & Tifenn Hirtzlin & Fr, 2024. "Powering AI at the edge: A robust, memristor-based binarized neural network with near-memory computing and miniaturized solar cell," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    19. Seokho Seo & Beomjin Kim & Donghoon Kim & Seungwoo Park & Tae Ryong Kim & Junkyu Park & Hakcheon Jeong & See-On Park & Taehoon Park & Hyeok Shin & Myung-Su Kim & Yang-Kyu Choi & Shinhyun Choi, 2022. "The gate injection-based field-effect synapse transistor with linear conductance update for online training," Nature Communications, Nature, vol. 13(1), pages 1-10, December.
    20. Bernhard Nessler & Michael Pfeiffer & Lars Buesing & Wolfgang Maass, 2013. "Bayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity," PLOS Computational Biology, Public Library of Science, vol. 9(4), pages 1-30, April.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-30305-8. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.