Keynote I

Date: 2 Jul 2025 (Wed)
Time: 18:00 - 19:00
Venue: Silverbox Ballroom, 1/F, Hotel ICON

Prof. Yang Chai

Associate Dean (FS) & Chair Professor of Semiconductor Physics

Title: How Microelectronics is Powering the AI Revolution?

Abstract

AI's explosive growth, from deep learning to generative large language models, relies fundamentally on hardware advancements, as breakthroughs in parallel processing (GPUs/TPUs), high-bandwidth memories (HBMs), and specialized accelerators have enabled the training of increasingly complex models. Conventional von Neumann architectures struggle with the energy inefficiency and latency of data movement, creating a critical bottleneck for AI scalability. Advances in microelectronics, including specialized accelerators (GPUs, TPUs), emerging memories (ReRAM, PCM), and neuromorphic devices, are enabling a paradigm shift toward parallel, in-memory, and brain-inspired computing. These innovations are not only accelerating AI workloads but also redefining the boundaries of energy-efficient, real-time processing.

In this talk, I will firstly introduce the basic knowledge of semiconductor devices for the audience without related backgrounds and explain the basic working principles of GPU, HBM, etc. Then I will focus on talking about the hardware implementation of AI sensors. The demand for accurate perception of the physical world leads to a dramatic increase in sensory nodes. However, the transmission of massive and unstructured sensory data from sensors to computing units poses great challenges in terms of power‐efficiency, transmission bandwidth, data storage, time latency, and security. To efficiently process massive sensory data, it is crucial to achieve data compression and structuring at the sensory terminals. In‐sensor computing integrates perception, memory, and processing functions within sensors, enabling sensory terminals to perform data compression and data structuring. I will describe our team’s efforts towards bioinspired in-sensor computing for artificial vision, including the framework of the in-sensor computing and the vision sensors for different scenarios, including visual adaptation, motion perception, as well as event-driven vision sensors for spiking neural network.

Biography

Prof. Yang Chai is the Chair Professor of Semiconductor Physics of the Hong Kong Polytechnic University. He is an IEEE Distinguished Lecturer, an IEEE Fellow, an Optica Fellow, the Vice President of the Physical Society of Hong Kong, a member of The Hong Kong Young Academy of Sciences, and an Associate Editor of ACS Nano. He is a receipt of the Falling Walls Science Breakthroughs in Engineering and Technology for his work on “Breaking the Wall of Efficient Sensory AI Systems”, the BOCHK Science and Technology Innovation Prize in the field of AI and Robotics, and NSFC Distinguished Young Scholar. His current research interest mainly focuses on emerging electronic devices.