|
|||||||||
![]() |
[SS #1] (13:15~14:30) October 22, 2020
Session Title : Design, Analysis and Tools for Integrated Circuits and Systems (DATICS)
Organizer : Prof. Ka Lok Man, Xi'an Jiaotong-Liverpool University, Suzhou, China
Abstract :
Session Title : Edge Computing for Smart IoT Systems: Device, Circuit, and System
Organizer : Prof. Tony Tae-Hyoung Kim, Nanyang Technological University, Singapore
Abstract :
Session Title : Design and Analysis of Nonlinear Circuits and Networks
Organizer : Prof. Yoshifumi Nishio, Tokushima University, Japan
Abstract :
From the beginning of the 20th century, plenty of design and analysis methods for nonlinear circuits and networks have been developed. However, we need more powerful tools to design low cost power electronic circuits, to analyze large scale complex nonlinear networks, and to realize more intelligent artificial neural networks.
In this special session, 5 papers are invited to show examples of recent works on design and analysis of such nonlinear circuits and networks.
[SS #4] (14:00~15:30) October 23, 2020
Session Title : Advanced Algorithms and Hardware Accelerators
Organizer : Robert Chen-Hao Chang, Program Director, Semiconductor Moonshot Project, MOST, Professor, Dept. of EE, National Chung Hsing University, Taiwan
Abstract :
Recently, the AI-based deep-learning hardware accelerator and advanced image processing technologies have revealed the unsurpassed importance in many application fields. To advance the algorithms and the circuit design technologies in practical applications, the off-the-shelf edge devices or instruments must strengthen their edge computing ability greatly by applying the advanced, smart, and effective processing solutions, which will contain the deep-learning based object detection and pattern recognition technologies, the deep-learning based hardware accelerator design, the advanced 3D pose estimation technology, the advanced semantic segmentation technology, the advanced image processing by blind-signal processing technology, etc. By utilizing the advanced algorithms and hardware accelerators, the wide application fields in our daily life will become smarter and efficient further.
[SS #5] (08:30~09:45) October 23, 2020
Session Title : Circuits and Theories for Neuromorphic, Non-linear, and Sensing Techniques
Organizer : Prof. Kyeong-Sik Min, Kookmin University, Seoul, Korea
Abstract :
In this special session, emerging techniques of neuromorphic, non-linear, and sensing circuits are discussed and presented. For realizing a brain-inspired technique, memristors and spin-orbit torque MRAMs are presented for a possible solution of neuromorphic circuits. And, a non-linear-circuit-based theory is explained as a potential tool for understanding brain’s behavior. And, a bio-sensing circuit is also discussed in this special session.
[SS #6] (15:30~16:45) October 23, 2020
Session Title : Artificial Intelligent and Security Systems
Organizer : Prof. Hanho Lee, Inha University, Korea
Abstract :
Recently, various applications such as AI, and machine learning, hardware security have emerged, opening up a new domain of integrated circuits design. This session presents fast prototyping method of a deep neural network on an FPGA, and efficient way to reduce the computational complexity of deep neural networks (DNNs) for attention based speech processing. Intel's Loihi neuromorphic research chip and its hardware systems are introduced and find out how they are applied and used in actual research fields. Also, this session presents an efficient architecture of number theoretic transform (NTT) for ring learning with error (R-LWE) based cryptosystems.