BIMSA >
Advances in Artificial Intelligence
Natural Phenomena to AI Breakthroughs: The Journey of Liquid Neural Networks
Natural Phenomena to AI Breakthroughs: The Journey of Liquid Neural Networks
Organizers
Speaker
Time
Thursday, October 17, 2024 2:00 PM - 4:00 PM
Venue
A3-1-301
Online
Zoom 230 432 7880
(BIMSA)
Abstract
Inspired by the nervous system of worms, MIT researchers proposed the model of Liquid Neural Networks (LNN) in 2006. In the years that followed, they developed a theoretical framework for LNNs, proving their superior theoretical properties and achieving successful applications in time series modeling, differential equation solving, and bioinformatics. Recently, they introduced Liquid Foundation Models (LFMs), a general AI model based on LNNs. LFMs are large neural networks built upon the theories of dynamical systems, signal processing, and numerical linear algebra. This unique combination allows LFMs to leverage decades of theoretical advances in these fields. The development from LNNs to LFMs illustrates a path from natural phenomena to mathematical models and eventually to AI products. This journey might offer us significant insights.
Speaker Intro
Sun Mingming is currently a professor at the Beijing Institute of Mathematical Sciences and Applications (BIMSA), focusing on fundamental research in artificial intelligence. Before this, he worked in the internet industry, engaging in AI research and development. He served as a Principal Researcher and Leader of the Cognitive Computing Lab at Baidu Research, where he led innovative research projects in cognitive natural language processing and autonomous driving systems, and oversaw the development of core subsystems for Baidu’s large language model, “Wenxin Yiyan”. He was also responsible for building the world-leading web search recommendation system for Baidu. He also developed several data analysis algorithms at Tencent. Sun Mingming’s achievements in the internet industry include receiving the Leading Science and Technology Award at the 2023 World Internet Conference and several top technical and product awards at Baidu. Before entering the internet industry, he taught at Nanjing University of Science and Technology as a lecturer and postdoctoral researcher.