EE Distinguished Speakers Seminar: Perspectives of 2D materials for machine learning chips
Event details
Date | 29.03.2019 |
Hour | 13:15 › 14:00 |
Speaker | Giuseppe Iannaccone is Professor of electronics at the University of Pisa, Italy, Fellow of the Institute of Electrical and Electronics Engineers, and Fellow of the American Physical Society. His interests include the fundamentals of transport and noise in nanoelectronic and mesoscopic devices, the development of device modeling and TCAD tools, and the design of extremely low-power circuits and systems for RFID and ambient intelligence scenarios. He has published more than 200 papers in peer-reviewed journals and more than 130 papers in proceedings of international conferences. Giuseppe Iannaccone has coordinated a few European and National Projects involving multiple partners and has acted as the Principal Investigator in several research projects funded by European and National public agencies and by private organizations. He is presently coordinating the QUEFORMAL FET h2020 project, Quantum Engineering for Machine Learning. Find more on him on www.iannaccone.org |
Location | |
Category | Conferences - Seminars |
Abstract: In this talk we will discuss the challenges, opportunities, and the performance potential of atomistic engineering of electron devices exploiting the fundamental properties of 2D material heterostructures, with a particular attention to computer architectures for machine learning applications.
The “materials-on-demand paradigm” based on the 2D materials is a modern evolution of what in the 1980s was called “band-gap engineering” or “band-structure engineering”, i.e., the artificial modification of band edge profiles using heterostructures made possible by epitaxial growth of III-V and II-VI material systems.
Lateral and vertical heterostructures of 2D materials could represent a revolutionary and enabling technology to device engineering providing the possibility to engineer transistors and memory at the atomistic scale, which we like to call “quantum engineering”.
We will show that the challenge of equipping devices at the edge of the cloud with cognitive capabilities requires dedicated machine learning chips and innovation in architectures, circuits and technology, for which heterostructures of 2D materials appear to be particularly well suited.
The “materials-on-demand paradigm” based on the 2D materials is a modern evolution of what in the 1980s was called “band-gap engineering” or “band-structure engineering”, i.e., the artificial modification of band edge profiles using heterostructures made possible by epitaxial growth of III-V and II-VI material systems.
Lateral and vertical heterostructures of 2D materials could represent a revolutionary and enabling technology to device engineering providing the possibility to engineer transistors and memory at the atomistic scale, which we like to call “quantum engineering”.
We will show that the challenge of equipping devices at the edge of the cloud with cognitive capabilities requires dedicated machine learning chips and innovation in architectures, circuits and technology, for which heterostructures of 2D materials appear to be particularly well suited.
Practical information
- General public
- Free
Organizer
- Prof. Elison Matioli