BEGIN:VCALENDAR VERSION:2.0 PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4// BEGIN:VEVENT UID:20260619T054204EDT-6660SlVWU6@132.216.98.100 DTSTAMP:20260619T094204Z DESCRIPTION:\n ISS Informal Systems Seminar\n\n  \n\n Speaker: Shuang Gao – Re search Fellow\, Simons Institute\, University of California\, Berkeley\, U nited States \n\n\n\n \n\n Abstract: This work connects models for virus spr ead on networks with their equivalent neural network representations. Base d on this connection\, we propose a new neural network architecture\, call ed Transmission Neural Networks (TransNNs)\, where activation functions ar e primarily associated with links and are allowed to have different activa tion levels. This connection also leads to the discovery and the derivatio n of three new activation functions with tunable or trainable parameters. We show that TransNNs with a single hidden layer and a fixed non-zero bias term are universal function approximators. Moreover\, we establish thresh old conditions for virus spread on networks where the dynamics are charact erized by TransNNs. Finally\, we present new fundamental derivations of co ntinuous time epidemic models on networks based on TransNNs.\n\n \n Biograph y: Shuang Gao received his PhD degree in Electrical Engineering from McGil l University under the supervision of Peter E. Caines. He was a postdoctor al researcher at ɬÀï·¬ from 2019 to 2022. He is currently a re search fellow at the Simons Institute for the Theory of Computing at the U niversity of California\, Berkeley. His research aims to discover fundamen tal properties of dynamics and control of systems that involve large popul ations of network-coupled agents or subsystems\, and achieve intelligent d ecision-making for such systems. His research interests lie in control\, g ames and learning for large networks (including those modeled by graphons) \, along with applications in social networks\, epidemic networks\, smart renewable energy grid and biological neural networks.\n\n DTSTART:20221021T180000Z DTEND:20221021T190000Z LOCATION:CA\, ZOOM SUMMARY:Transmission Neural Networks: From Virus Spread Models to Neural Ne tworks URL:/cim/channels/event/transmission-neural-networks-v irus-spread-models-neural-networks-351658 END:VEVENT END:VCALENDAR