FETs for Analog Neural MACs

Autor: Rinku Rani Das, T. R. Rajalekshmi, Sruthi Pallathuvalappil, Alex James
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: IEEE Access, Vol 12, Pp 54019-54048 (2024)
Druh dokumentu: article
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2024.3387094
Popis: This study provides a comprehensive view on neural network systems with implemented with crossbar circuits, and device-level understanding of modern FET technologies in neuromorphic computing. This work categorizes and analyzes various transistor types, including ion-gate, ferroelectric, and floating-gate transistors, shedding light on their unique advantages and applications in neuromorphic computing. In this overview, we explore the fundamental principles, recent advancements, and significant trends in transistor-based neuromorphic devices, providing valuable insights into this innovative field. This work also examines resistive memories and 2D materials, that could revolutionize transistor fabrication for neuromorphic devices. Further, various research challenges, limitations, and potential research directions are discussed.
Databáze: Directory of Open Access Journals