Feng Ling's website

I am curious of the interesting things emerging from complex things, like intelligence from neural networks, consensus and utility from public blockchains, viral spreading from social networks, mobility patterns from urban systems -- and also interested in improving them.

Currently I am a principal scientist leading the complex systems group at the Institute of High Performance Computing, A*STAR Singapore, and adjunct assistant professor in physics at the National University of Singapore.

Intelligence at critical point

My research on AI focuses on the complexity science and dynamics of deep learning models. Drawing from and dynamical systems and spin glasses, my work investigates how neural networks achieve optimal intelligence and generalization at the "edge of chaos" – the critical boundary between ordered and chaotic phases. This principle, inspired by natural systems like the brain, reveals that machine learning models perform best when their asymptotic stability hovers at this transition point, maximizing information processing and adaptability. In "Optimal Machine Intelligence at the Edge of Chaos" (2020), we develop…

Blockchains

Public blockchains (also mistakenly confused with crypto currencies) are in a sense, inevitable evolution of techno-social phenomena that likely will revolutionize various key aspects of our social economic life. Like many social phenomena, they emerge out of a large number of people; unlike many social phenomena, they are prevailing exponentially fast due to the underlying technology: internet, maths (hashing, zero-knowledge proof, etc.), and the ever growing needs for consensus/truth. One aspect I have been looking into is the self-organization patterns and mechanisms in blockchain ecosystems, in particular the evolution of…

Social networks

Urban systems