Modelling in-device inference and classification of binary digits using nonlinear dynamics of spin Hall oscillator
- Resource Type
- Conference
- Authors
- Mohan, John Rex; Yamanaka, Chisato; Feng, Ryoyan; Mathew, Arun Jacob; Nakamura, Yoji; Medwal, Rohit; Gupta, Surbhi; Rawat, Rajdeep Singh; Fukuma, Yasuhiro
- Source
- 2023 IEEE International Magnetic Conference - Short Papers (INTERMAG Short Papers) Magnetic Conference - Short Papers (INTERMAG Short Papers), 2023 IEEE International. :1-2 May, 2023
- Subject
- Fields, Waves and Electromagnetics
Image recognition
Neuromorphics
Magnetization
Magnetic resonance imaging
Heuristic algorithms
Nonlinear dynamical systems
Micromagnetics
Neuromorphic computing
nonlinear magnetization dynamics
spin Hall oscillator
The MNIST handwritten digit classification
- Language
In this work, we employ micromagnetic modelling of a spin Hall oscillator for a direct inference and classification of binary digit inputs. The spectral characteristics of the oscillation is utilized for the classification. We observed a direct inference of binary digit inputs up to a sequence of four binary digits. Subsequently, handwritten digit image recognition is tested with the Modified National Institute of Standards and Testing (MNIST) handwritten digit database and acquired an accuracy of 88.6% with a linear classifier network.