Spintronic Devices for Neuromorphic Computing

Loading...
Thumbnail Image

Persistent link to this item

Statistics
View Statistics

Journal Title

Journal ISSN

Volume Title

Title

Spintronic Devices for Neuromorphic Computing

Published Date

2020-07

Publisher

Type

Thesis or Dissertation

Abstract

Neuromorphic and spintronic computing are two different technologies that have progressed significantly in recent years. The former has seen advancement in algorithms and hardware implementations that solve previously intractable problems in data processing and classification, while the latter has seen the advent of an entirely new class of physical computing primitives. In particular, spin-torque-switched magnetic tunnel junctions and magnetelectric-ferromagnetic heterostructures are promising candidates for neuromimetic devices. Using physics-based model simulations of SHE-MTJ and ME-FM circuits, I predict the performance of various spintronic neural network formulations on standard benchmarking tasks and show that circuits like these are likely to be the neuromorphic hardware of the future.

Description

University of Minnesota Ph.D. dissertation.July 2020. Major: Electrical Engineering. Advisor: Steven Koester. 1 computer file (PDF); ix, 142 pages.

Related to

Replaces

License

Collections

Series/Report Number

Funding information

Isbn identifier

Doi identifier

Previously Published Citation

Suggested citation

Stephan, Andrew. (2020). Spintronic Devices for Neuromorphic Computing. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/241706.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.