학술논문

Multistable neuromorphic computing: controlling attractor switches using waveforms
Document Type
Conference
Source
2022 International Electron Devices Meeting (IEDM) Electron Devices Meeting (IEDM), 2022 International. :21.3.1-21.3.4 Dec, 2022
Subject
Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Neuromorphic engineering
Switches
Computer architecture
Control systems
Energy efficiency
Electron devices
Language
ISSN
2156-017X
Abstract
An important question in designing multistable neuromorphic computing devices is how best to switch between attractors. We demonstrate that waveform-based stimuli are more energy-efficient than single pulses and can target all attractors, allowing for the possibility of developing non-von Neumann neuromorphic circuit architectures that incorporate both digital and analog components.