Neuromorphic computing, which aims to replicate the computational structure and architecture of the brain in synthetic hardware, has typically focused on artificial intelligence applications. What is less explored is whether such brain-inspired hardware can provide value beyond cognitive tasks. Here we show that the high degree of parallelism and configurability of spiking neuromorphic architectures makes them well suited to implement random walks via discrete-time Markov chains. Overall, these random walks are useful in Monte Carlo methods, which represent a fundamental computational tool for solving a wide range of numerical computing tasks. Using IBM’s TrueNorth and Intel’s Loihi neuromorphic computing platforms, we show that our neuromorphic computing algorithm for generating random walk approximations of diffusion offers advantages in energy-efficient computation compared with conventional approaches. We also show that our neuromorphic computing algorithm can be extended to more sophisticated jump-diffusion processes that are useful in a range of applications, including financial economics, particle physics and machine learning.
Smith, J. Darby, et al. "Neuromorphic scaling advantages for energy-efficient random walk computations." Nature Electronics, vol. 5, no. 2, Feb. 2022. https://doi.org/10.1038/s41928-021-00705-7
Smith, J. Darby, Hill, Aaron J., Reeder, Leah E., Franke, Brian C., Lehoucq, Richard B., Parekh, Ojas, Severa, William, & Aimone, James B. (2022). Neuromorphic scaling advantages for energy-efficient random walk computations. Nature Electronics, 5(2). https://doi.org/10.1038/s41928-021-00705-7
Smith, J. Darby, Hill, Aaron J., Reeder, Leah E., et al., "Neuromorphic scaling advantages for energy-efficient random walk computations," Nature Electronics 5, no. 2 (2022), https://doi.org/10.1038/s41928-021-00705-7
@article{osti_1845387,
author = {Smith, J. Darby and Hill, Aaron J. and Reeder, Leah E. and Franke, Brian C. and Lehoucq, Richard B. and Parekh, Ojas and Severa, William and Aimone, James B.},
title = {Neuromorphic scaling advantages for energy-efficient random walk computations},
annote = {Neuromorphic computing, which aims to replicate the computational structure and architecture of the brain in synthetic hardware, has typically focused on artificial intelligence applications. What is less explored is whether such brain-inspired hardware can provide value beyond cognitive tasks. Here we show that the high degree of parallelism and configurability of spiking neuromorphic architectures makes them well suited to implement random walks via discrete-time Markov chains. Overall, these random walks are useful in Monte Carlo methods, which represent a fundamental computational tool for solving a wide range of numerical computing tasks. Using IBM’s TrueNorth and Intel’s Loihi neuromorphic computing platforms, we show that our neuromorphic computing algorithm for generating random walk approximations of diffusion offers advantages in energy-efficient computation compared with conventional approaches. We also show that our neuromorphic computing algorithm can be extended to more sophisticated jump-diffusion processes that are useful in a range of applications, including financial economics, particle physics and machine learning.},
doi = {10.1038/s41928-021-00705-7},
url = {https://www.osti.gov/biblio/1845387},
journal = {Nature Electronics},
issn = {ISSN 2520-1131},
number = {2},
volume = {5},
place = {United States},
publisher = {Springer Nature},
year = {2022},
month = {02}}
Schemmel, Johannes; Briiderle, Daniel; Griibl, Andreas
2010 IEEE International Symposium on Circuits and Systems - ISCAS 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systemshttps://doi.org/10.1109/ISCAS.2010.5536970
Parekh, Ojas; Phillips, Cynthia A.; James, Conrad D.
SPAA '18: 30th ACM Symposium on Parallelism in Algorithms and Architectures, Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectureshttps://doi.org/10.1145/3210377.3210410
Aimone, James B.; Parekh, Ojas; Phillips, Cynthia A.
ICONS '19: International Conference on Neuromorphic Systems, Proceedings of the International Conference on Neuromorphic Systemshttps://doi.org/10.1145/3354265.3354285
ICONS '19: International Conference on Neuromorphic Systems, Proceedings of the International Conference on Neuromorphic Systemshttps://doi.org/10.1145/3354265.3354269
Aimone, James B.; Severa, William; Vineyard, Craig M.
ICONS '19: International Conference on Neuromorphic Systems, Proceedings of the International Conference on Neuromorphic Systemshttps://doi.org/10.1145/3354265.3354268