Probabilistic Neural Computing with Stochastic Devices

Misra, Shashank; Bland, Leslie C.; Cardwell, Suma G.; Incorvia, Jean Anne C.; James, Conrad D.; Kent, Andrew D.; Schuman, Catherine D.; Smith, J. Darby; Aimone, James B.

doi:10.1002/adma.202204569

Title: Probabilistic Neural Computing with Stochastic Devices

Journal Article · Thu Nov 17 00:00:00 EST 2022 · Advanced Materials

DOI:https://doi.org/10.1002/adma.202204569· OSTI ID:1898714

^[1];

^[2];

^[3];

^[4]; James, Conrad D. ^[1];

^[5];

^[6];

^[3];

^[3]

Microsystems Engineering, Science and Applications Sandia National Laboratories Albuquerque NM 87123 USA
Department of Physics Temple University Philadelphia PA 19122‐1801 USA
Neural Exploration and Research Laboratory Sandia National Laboratories Albuquerque NM 87123 USA
Department of Electrical and Computer Engineering The University of Texas at Austin Austin TX 78712 USA
Department of Physics New York University New York NY 10003 USA
Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN 37996 USA

Abstract The brain has effectively proven a powerful inspiration for the development of computing architectures in which processing is tightly integrated with memory, communication is event‐driven, and analog computation can be performed at scale. These neuromorphic systems increasingly show an ability to improve the efficiency and speed of scientific computing and artificial intelligence applications. Herein, it is proposed that the brain's ubiquitous stochasticity represents an additional source of inspiration for expanding the reach of neuromorphic computing to probabilistic applications. To date, many efforts exploring probabilistic computing have focused primarily on one scale of the microelectronics stack, such as implementing probabilistic algorithms on deterministic hardware or developing probabilistic devices and circuits with the expectation that they will be leveraged by eventual probabilistic architectures. A co‐design vision is described by which large numbers of devices, such as magnetic tunnel junctions and tunnel diodes, can be operated in a stochastic regime and incorporated into a scalable neuromorphic architecture that can impact a number of probabilistic computing applications, such as Monte Carlo simulations and Bayesian neural networks. Finally, a framework is presented to categorize increasingly advanced hardware‐based probabilistic computing technologies.

View Journal Article

Cite

Export

Save

Sponsoring Organization:: USDOE

OSTI ID:: 1898714

Alternate ID(s):: OSTI ID: 1898715

Journal Information:: Advanced Materials, Journal Name: Advanced Materials Vol. 35 Journal Issue: 37; ISSN 0935-9648

Publisher:: Wiley Blackwell (John Wiley & Sons)Copyright Statement

Country of Publication:: Germany

Language:: English

References (66)

Neural Dynamics as Sampling: A Model for Stochastic Computation in Recurrent Networks of Spiking Neurons Buesing, Lars; Bill, Johannes; Nessler, Bernhard PLoS Computational Biology, Vol. 7, Issue 11 https://doi.org/10.1371/journal.pcbi.1002211	journal	November 2011
Neuro-Inspired Computing With Emerging Nonvolatile Memorys Yu, Shimeng Proceedings of the IEEE, Vol. 106, Issue 2 https://doi.org/10.1109/JPROC.2018.2790840	journal	February 2018
Stochastic computing elements and systems Poppelbaum, W. J.; Afuso, C.; Esch, J. W. Proceedings of the November 14-16, 1967, fall joint computer conference on - AFIPS '67 (Fall) https://doi.org/10.1145/1465611.1465696	conference	January 1967
Quantum random number generators Herrero-Collantes, Miguel; Garcia-Escartin, Juan Carlos Reviews of Modern Physics, Vol. 89, Issue 1 https://doi.org/10.1103/RevModPhys.89.015004	journal	February 2017
Memristive crossbar arrays for brain-inspired computing Xia, Qiangfei; Yang, J. Joshua Nature Materials, Vol. 18, Issue 4 https://doi.org/10.1038/s41563-019-0291-x	journal	March 2019
Probabilistic computing with p-bits Kaiser, Jan; Datta, Supriyo Applied Physics Letters, Vol. 119, Issue 15 https://doi.org/10.1063/5.0067927	journal	October 2021
Stochastic computing Gaines, B. R. Proceedings of the April 18-20, 1967, spring joint computer conference on - AFIPS '67 (Spring) https://doi.org/10.1145/1465482.1465505	conference	January 1967
Nonuniform probability of glutamate release at a hippocampal synapse Rosenmund, C.; Clements, J.; Westbrook, G. Science, Vol. 262, Issue 5134 https://doi.org/10.1126/science.7901909	journal	October 1993
Voltage-Controlled Spintronic Stochastic Neuron Based on a Magnetic Tunnel Junction Cai, Jialin; Fang, Bin; Zhang, Like Physical Review Applied, Vol. 11, Issue 3 https://doi.org/10.1103/PhysRevApplied.11.034015	journal	March 2019
Sneak, discharge, and leakage current issues in a high-dimensional 1T1M memristive crossbar Demin, V. A.; Surazhevsky, I. A.; Emelyanov, A. V. Journal of Computational Electronics, Vol. 19, Issue 2 https://doi.org/10.1007/s10825-020-01470-0	journal	March 2020
Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines Neftci, Emre O.; Pedroni, Bruno U.; Joshi, Siddharth Frontiers in Neuroscience, Vol. 10 https://doi.org/10.3389/fnins.2016.00241	journal	June 2016
Neuromorphic scaling advantages for energy-efficient random walk computations Smith, J. Darby; Hill, Aaron J.; Reeder, Leah E. Nature Electronics, Vol. 5, Issue 2 https://doi.org/10.1038/s41928-021-00705-7	journal	February 2022
GPU implementation of neural networks Oh, Kyoung-Su; Jung, Keechul Pattern Recognition, Vol. 37, Issue 6 https://doi.org/10.1016/j.patcog.2004.01.013	journal	June 2004
Massively parallel ultrafast random bit generation with a chip-scale laser Kim, Kyungduk; Bittner, Stefan; Zeng, Yongquan Science, Vol. 371, Issue 6532 https://doi.org/10.1126/science.abc2666	journal	February 2021
Opportunities for neuromorphic computing algorithms and applications Schuman, Catherine D.; Kulkarni, Shruti R.; Parsa, Maryam Nature Computational Science, Vol. 2, Issue 1 https://doi.org/10.1038/s43588-021-00184-y	journal	January 2022
Survey on hardware implementation of random number generators on FPGA: Theory and experimental analyses Bakiri, Mohammed; Guyeux, Christophe; Couchot, Jean-François Computer Science Review, Vol. 27 https://doi.org/10.1016/j.cosrev.2018.01.002	journal	February 2018
Hippocampal Reactivation of Random Trajectories Resembling Brownian Diffusion Stella, Federico; Baracskay, Peter; O’Neill, Joseph Neuron, Vol. 102, Issue 2 https://doi.org/10.1016/j.neuron.2019.01.052	journal	April 2019
Survey of Stochastic Computing Alaghi, Armin; Hayes, John P. ACM Transactions on Embedded Computing Systems, Vol. 12, Issue 2s https://doi.org/10.1145/2465787.2465794	journal	May 2013
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images Geman, Stuart; Geman, Donald IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-6, Issue 6 https://doi.org/10.1109/TPAMI.1984.4767596	journal	November 1984
Physics for neuromorphic computing Marković, Danijela; Mizrahi, Alice; Querlioz, Damien Nature Reviews Physics, Vol. 2, Issue 9 https://doi.org/10.1038/s42254-020-0208-2	journal	July 2020
Independent Sources of Quantal Variability at Single Glutamatergic Synapses Franks, Kevin M.; Stevens, Charles F.; Sejnowski, Terrence J. The Journal of Neuroscience, Vol. 23, Issue 8 https://doi.org/10.1523/JNEUROSCI.23-08-03186.2003	journal	April 2003
Autonomous Probabilistic Coprocessing With Petaflips per Second Sutton, Brian; Faria, Rafatul; Ghantasala, Lakshmi Anirudh IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.3018682	journal	January 2020
A review of uncertainty quantification in deep learning: Techniques, applications and challenges Abdar, Moloud; Pourpanah, Farhad; Hussain, Sadiq Information Fusion, Vol. 76 https://doi.org/10.1016/j.inffus.2021.05.008	journal	December 2021
Impermanence of dendritic spines in live adult CA1 hippocampus Attardo, Alessio; Fitzgerald, James E.; Schnitzer, Mark J. Nature, Vol. 523, Issue 7562 https://doi.org/10.1038/nature14467	journal	June 2015
In situ learning using intrinsic memristor variability via Markov chain Monte Carlo sampling Dalgaty, Thomas; Castellani, Niccolo; Turck, Clément Nature Electronics, Vol. 4, Issue 2 https://doi.org/10.1038/s41928-020-00523-3	journal	January 2021
Demonstration of Nanosecond Operation in Stochastic Magnetic Tunnel Junctions Safranski, Christopher; Kaiser, Jan; Trouilloud, Philip Nano Letters, Vol. 21, Issue 5 https://doi.org/10.1021/acs.nanolett.0c04652	journal	February 2021
In-memory computing with resistive switching devices Ielmini, Daniele; Wong, H. -S. Philip Nature Electronics, Vol. 1, Issue 6 https://doi.org/10.1038/s41928-018-0092-2	journal	June 2018
Parallel programming of an ionic floating-gate memory array for scalable neuromorphic computing Fuller, Elliot J.; Keene, Scott T.; Melianas, Armantas Science, Vol. 364, Issue 6440 https://doi.org/10.1126/science.aaw5581	journal	April 2019
Assessing a Neuromorphic Platform for use in Scientific Stochastic Sampling Aimone, James B.; Lehoucq, Richard; Severa, William 2021 International Conference on Rebooting Computing (ICRC) https://doi.org/10.1109/ICRC53822.2021.00019	conference	November 2021
Extracting random numbers from quantum tunnelling through a single diode Bernardo-Gavito, Ramón; Bagci, Ibrahim Ethem; Roberts, Jonathan Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-18161-9	journal	December 2017
Composable Probabilistic Inference Networks Using MRAM-based Stochastic Neurons Zand, Ramtin; Camsari, Kerem Y.; Datta, Supriyo ACM Journal on Emerging Technologies in Computing Systems, Vol. 15, Issue 2 https://doi.org/10.1145/3304105	journal	March 2019
A new spin on magnetic memories Kent, Andrew D.; Worledge, Daniel C. Nature Nanotechnology, Vol. 10, Issue 3 https://doi.org/10.1038/nnano.2015.24	journal	March 2015
Silicon quantum electronics Zwanenburg, Floris A.; Dzurak, Andrew S.; Morello, Andrea Reviews of Modern Physics, Vol. 85, Issue 3 https://doi.org/10.1103/RevModPhys.85.961	journal	July 2013
Modern Monte Carlo methods for efficient uncertainty quantification and propagation: A survey Zhang, Jiaxin WIREs Computational Statistics, Vol. 13, Issue 5 https://doi.org/10.1002/wics.1539	journal	December 2020
Improved signaling as a result of randomness in synaptic vesicle release Zhang, Calvin; Peskin, Charles S. Proceedings of the National Academy of Sciences, Vol. 112, Issue 48 https://doi.org/10.1073/pnas.1513160112	journal	November 2015
Neural sampling machine with stochastic synapse allows brain-like learning and inference Dutta, Sourav; Detorakis, Georgios; Khanna, Abhishek Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-30305-8	journal	May 2022
$\mu $ RNG: A 300–950 mV, 323 Gbps/W All-Digital Full-Entropy True Random Number Generator in 14 nm FinFET CMOS Mathew, Sanu K.; Johnston, David; Satpathy, Sudhir IEEE Journal of Solid-State Circuits, Vol. 51, Issue 7 https://doi.org/10.1109/JSSC.2016.2558490	journal	July 2016
A Roadmap for Reaching the Potential of Brain‐Derived Computing Aimone, James B. Advanced Intelligent Systems, Vol. 3, Issue 1 https://doi.org/10.1002/aisy.202000191	journal	November 2020
Nanosecond Random Telegraph Noise in In-Plane Magnetic Tunnel Junctions Hayakawa, K.; Kanai, S.; Funatsu, T. Physical Review Letters, Vol. 126, Issue 11 https://doi.org/10.1103/PhysRevLett.126.117202	journal	March 2021
Low-Energy Deep Belief Networks Using Intrinsic Sigmoidal Spintronic-based Probabilistic Neurons Zand, Ramtin; Camsari, Kerem Yunus; Pyle, Steven D. GLSVLSI '18: Great Lakes Symposium on VLSI 2018, Proceedings of the 2018 on Great Lakes Symposium on VLSI https://doi.org/10.1145/3194554.3194558	conference	May 2018
Dark Silicon and the End of Multicore Scaling Esmaeilzadeh, H.; Blem, E.; St. Amant, R. IEEE Micro, Vol. 32, Issue 3 https://doi.org/10.1109/MM.2012.17	journal	May 2012
ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars Shafiee, Ali; Nag, Anirban; Muralimanohar, Naveen ACM SIGARCH Computer Architecture News, Vol. 44, Issue 3 https://doi.org/10.1145/3007787.3001139	journal	June 2016
EPOS LHC: Test of collective hadronization with data measured at the CERN Large Hadron Collider Pierog, T.; Karpenko, Iu.; Katzy, J. M. Physical Review C, Vol. 92, Issue 3 https://doi.org/10.1103/PhysRevC.92.034906	journal	September 2015
Nonideality‐Aware Training for Accurate and Robust Low‐Power Memristive Neural Networks Joksas, Dovydas; Wang, Erwei; Barmpatsalos, Nikolaos Advanced Science, Vol. 9, Issue 17 https://doi.org/10.1002/advs.202105784	journal	May 2022
The hardware lottery Hooker, Sara Communications of the ACM, Vol. 64, Issue 12 https://doi.org/10.1145/3467017	journal	December 2021
Using machine learning as a surrogate model for agent-based simulations Angione, Claudio; Silverman, Eric; Yaneske, Elisabeth PLOS ONE, Vol. 17, Issue 2 https://doi.org/10.1371/journal.pone.0263150	journal	February 2022
Moore's law: past, present and future Schaller, R. R. IEEE Spectrum, Vol. 34, Issue 6 https://doi.org/10.1109/6.591665	journal	June 1997
A High-Yield $\hbox{HfO}_{x}$-Based Unipolar Resistive RAM Employing Ni Electrode Compatible With Si-Diode Selector for Crossbar Integration Tran, X. A.; Yu, H. Y.; Yeo, Y. C. IEEE Electron Device Letters, Vol. 32, Issue 3 https://doi.org/10.1109/LED.2010.2099205	journal	March 2011
Graphics processing unit (GPU) programming strategies and trends in GPU computing Brodtkorb, André R.; Hagen, Trond R.; Sætra, Martin L. Journal of Parallel and Distributed Computing, Vol. 73, Issue 1 https://doi.org/10.1016/j.jpdc.2012.04.003	journal	January 2013
An All-Memristor Deep Spiking Neural Computing System: A Step Toward Realizing the Low-Power Stochastic Brain Wijesinghe, Parami; Ankit, Aayush; Sengupta, Abhronil IEEE Transactions on Emerging Topics in Computational Intelligence, Vol. 2, Issue 5 https://doi.org/10.1109/TETCI.2018.2829924	journal	October 2018
Parton fragmentation and string dynamics Andersson, B.; Gustafson, G.; Ingelman, G. Physics Reports, Vol. 97, Issue 2-3 https://doi.org/10.1016/0370-1573(83)90080-7	journal	July 1983
Low-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional Computing Vodenicarevic, D.; Locatelli, N.; Mizrahi, A. Physical Review Applied, Vol. 8, Issue 5 https://doi.org/10.1103/PhysRevApplied.8.054045	journal	November 2017
Fluctuations in Bistable Tunnel Diode Circuits Landauer, R. Journal of Applied Physics, Vol. 33, Issue 7 https://doi.org/10.1063/1.1728929	journal	July 1962
The Sad History of Random Bits Markowsky, George Journal of Cyber Security and Mobility, Vol. 3, Issue 1 https://doi.org/10.13052/jcsm2245-1439.311	journal	January 2014
Integer factorization using stochastic magnetic tunnel junctions Borders, William A.; Pervaiz, Ahmed Z.; Fukami, Shunsuke Nature, Vol. 573, Issue 7774 https://doi.org/10.1038/s41586-019-1557-9	journal	September 2019
The Monte Carlo Method Metropolis, Nicholas; Ulam, S. Journal of the American Statistical Association, Vol. 44, Issue 247 https://doi.org/10.1080/01621459.1949.10483310	journal	September 1949
Stochastic Memory Devices for Security and Computing Carboni, Roberto; Ielmini, Daniele Advanced Electronic Materials, Vol. 5, Issue 9 https://doi.org/10.1002/aelm.201900198	journal	November 2018
Massively parallel probabilistic computing with sparse Ising machines Aadit, Navid Anjum; Grimaldi, Andrea; Carpentieri, Mario Nature Electronics, Vol. 5, Issue 7 https://doi.org/10.1038/s41928-022-00774-2	journal	June 2022
Understanding the Metropolis-Hastings Algorithm Chib, Siddhartha; Greenberg, Edward The American Statistician, Vol. 49, Issue 4 https://doi.org/10.2307/2684568	journal	November 1995
Overview of Beyond-CMOS Devices and a Uniform Methodology for Their Benchmarking Nikonov, Dmitri E.; Young, Ian A. Proceedings of the IEEE, Vol. 101, Issue 12 https://doi.org/10.1109/JPROC.2013.2252317	journal	December 2013
Neural algorithms and computing beyond Moore's law Aimone, James B. Communications of the ACM, Vol. 62, Issue 4 https://doi.org/10.1145/3231589	journal	March 2019
Hardware-Aware In Situ Learning Based on Stochastic Magnetic Tunnel Junctions Kaiser, Jan; Borders, William A.; Camsari, Kerem Y. Physical Review Applied, Vol. 17, Issue 1 https://doi.org/10.1103/PhysRevApplied.17.014016	journal	January 2022
Multiscale Co-Design Analysis of Energy, Latency, Area, and Accuracy of a ReRAM Analog Neural Training Accelerator Marinella, Matthew J.; Agarwal, Sapan; Hsia, Alexander IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Vol. 8, Issue 1 https://doi.org/10.1109/JETCAS.2018.2796379	journal	March 2018
The probability of transmitter release at a mammalian central synapse Hessler, Neal A.; Shirke, Aneil M.; Malinow, Roberto Nature, Vol. 366, Issue 6455 https://doi.org/10.1038/366569a0	journal	December 1993
From biased coin to any discrete distribution Gryszka, Karol Periodica Mathematica Hungarica, Vol. 83, Issue 1 https://doi.org/10.1007/s10998-020-00363-w	journal	October 2020
Energy Scaling Advantages of Resistive Memory Crossbar Based Computation and Its Application to Sparse Coding Agarwal, Sapan; Quach, Tu-Thach; Parekh, Ojas Frontiers in Neuroscience, Vol. 9 https://doi.org/10.3389/fnins.2015.00484	journal	January 2016

Similar Records

Will Stochastic Devices Play Nice With Others in Neuromorphic Hardware?: There’s More to a Probabilistic System Than Noisy Devices

Journal Article · Fri Sep 01 00:00:00 EDT 2023 · IEEE Electron Devices Magazine · OSTI ID:1898714

Aimone, James B.; Misra, Shashank

Neural Algorithms for Low Power Implementation of Partial Differential Equations

Technical Report · Sat Sep 01 00:00:00 EDT 2018 · OSTI ID:1898714

Aimone, James Bradley; Hill, Aaron Jamison; Lehoucq, Richard B.; +3 more

Neuromorphic scaling advantages for energy-efficient random walk computations

Technical Report · Tue Sep 01 00:00:00 EDT 2020 · OSTI ID:1898714

Smith, John Darby; Hill, Aaron Jamison; Reeder, Leah; +5 more

Title: Probabilistic Neural Computing with Stochastic Devices

Citation Formats

References (66)

Similar Records

Related Subjects