Mode: Mixed
In the quest for truly intelligent computing, we’ve discovered that the most powerful breakthroughs emerge when two complementary systems “dance” together rather than working in isolation. This talk presents four distinct research achievements that surprisingly share a common thread: dual-system collaboration. We demonstrate (1) brain-machine co-evolution enabling real-time drone control with 20% performance gains, (2) data-hardware co-alignment through adaptive ADCs achieving 146× energy efficiency, (3) noise-driven dual-network training reducing power by 21×, and (4) security-compute co-location on RRAM chips saving 17.6× area. Beyond individual technical merits, these works reveal a fundamental design principle spanning from biological to artificial intelligence: true intelligence doesn’t arise from perfecting single systems, but from orchestrating the dance between complementary partners. This insight opens new pathways for neuromorphic computing, brain-computer interfaces, and human-machine collaborative intelligence.
Professor Ngai Wong received B.Eng. and Ph.D. degrees in electrical and electronic engineering from The University of Hong Kong (HKU), where he is currently Associate Professor. He has served as Associate Editor of IEEE Transactions on Computer-Aided Design since 2014 and regularly chairs technical program committees at premier EDA conferences including DAC, ICCAD, and ASP-DAC. He co-founded IEEE CEDA Hong Kong Chapter (2016) and served as Chair (2018/19). As Director of AVNET-HKU Emerging Microelectronics & Ubiquitous Systems (EMUS) Lab (launched 2025), his research spans compact neural networks and compute-in-memory AI chips. He coordinates the Hong Kong Theme-based Research Scheme “ReRACE: ReRAM AI Chips on the Edge” (2022-2027), advancing neuromorphic computing.
Clean water and clean air are vital for public health. This project focuses on developing high-efficiency and environmentally sustainable filters for removing harmful air/water pollutants. The team has developed novel architectures and functionalities for the filters to achieve high permeance, high removal efficiency, and excellent reusability.
