IEEE Swiss ED DL Lecture by Prof. Mansun Chan

#neuromorphic #computing #memory #devices #circuit #simulation
Share

Seminar title: Modeling of Memory Device with Bistable Dynamic Time Varying Characteristics

Abstract: The field of neuromorphic computing has rapidly advanced in recent years, driving a significant demand for memory array simulation. However, the existing circuit simulation methodology is not optimized for the unique characteristics of memory devices, which are time-varying and possess multiple outputs for the same input, depending on the internal state of the device. This has created a need for a new memory modeling platform that can capture these dynamic changes and multiple internal states. In this presentation, we will discuss the simulation infrastructure required for such memory modeling, along with recent progress in the development of neural network models that can quickly capture the characteristics of memory devices.

 



  Date and Time

  Location

  Hosts

  Registration



  • Date: 06 Jun 2023
  • Time: 02:00 PM to 03:30 PM
  • All times are (UTC+01:00) Bern
  • Add_To_Calendar_icon Add Event to Calendar
  • EPFL Lausanne
  • Lausanne, Switzerland
  • Switzerland 1015 Lausanne
  • Building: ELB
  • Room Number: 328
  • Click here for Map

  • Contact Event Host
  • Co-sponsored by Jean-Michel Sallese


  Speakers

Mansun Chan Mansun Chan of Dept. of ECE, Hong Kong University of Science & Technology

Topic:

Modeling of Memory Device with Bistable Dynamic Time Varying Characteristics

The field of neuromorphic computing has rapidly advanced in recent years, driving a significant demand for memory array simulation. However, the existing circuit simulation methodology is not optimized for the unique characteristics of memory devices, which are time-varying and possess multiple outputs for the same input, depending on the internal state of the device. This has created a need for a new memory modeling platform that can capture these dynamic changes and multiple internal states. In this presentation, we will discuss the simulation infrastructure required for such memory modeling, along with recent progress in the development of neural network models that can quickly capture the characteristics of memory devices.

Biography:

Prof. Mansun Chan received his PhD from the University of California at Berkeley.  Subsequently, he joined the Hong Kong University of Science and Technology and he is now the Alex Wong Siu Wah Gigi Wong Fook Chi Professor of Engineering and Chair Professor of the Department of Electronic and Computer Engineering.  He was one of the major contributors to the unified BSIM model for SPICE, which has been accepted by most US companies and the Compact Model Council (CMC) as the first industrial standard MOSFET model. His current research interests include emerging nano-device technologies, 2-D device for flexible electronics, CMOS interconnect technology, Artificial Neural Network systems, new-generation memory technology, BioNEMS, device modeling and ultra-low power circuit techniques.  He is a Distinguished Lecturer of IEEE, Fellow of IET and Fellow of IEEE.

Email:

Address:Dept. of ECE, Hong Kong University of Science & Technology, , Clear Water Bay, Kowloon, Hong Kong, Hong Kong