BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:7446-1391@rg-aachen.gi.de
CLASS: PUBLIC
SUMMARY:Biologically Plausible Large Language Models - Prof. Dr. Radu Grosu
  (TU Wien)
DESCRIPTION:In this talk I will present our journey at TUW towards construc
 ting a biologically plausible Large Language Model.\n\nI will start with th
 e Electrical-Equivalent-Circuit model used in Neuroscience, and discuss how
  this model can be restated as a NeuralODE, in the form of a Liquid Time Co
 nstant Neural Network (LTC). Using LTCs I will demonstrate how one can solv
 e various robotic tasks, including autonomous lane keeping with only 19 neu
 rons. I will then show how to dramatically speed up convergence and accurac
 y, in the setting of Liquid- Resistance Liquid-Capacitance Neural Networks 
 (LRCs).\n\nFinally, I will show how to scale up any recurrent nonlinear neu
 ral network, including our LRCs, to a Large Language Model, in form of a St
 ructured State Space Model (LrcSSM).\n\n\n\nAbout the speaker\n\nThe resear
 ch interests of Radu Grosu include the modeling, the analysis and the contr
 ol of cyber-physical systems and of biological systems.\n\nThe applications
  focus of Radu Grosu includes smart-mobility, Industry 4.0, smart-buildings
 , smart-agriculture, smart-healthcare, smart-cities, IoT, cardiac and neura
 l networks, and genetic regulatory networks.\n\nRadu Grosu among others is 
 recipient of the NSF Career Award, and the ACM Service Award. He is an elec
 ted member of the IFIP, Working Group 2.2.\n\n\n\nInvitation of Informatik 
 RWTH, RIA and Regina\n\n\n\nFor this talk, there is no video available.
LOCATION:Hörsaal AH IV, Informatik-Zentrum Hauptbau Hörn, Eingang Ahornstra
 ße
DTSTAMP:20251217T094225Z
DTSTART:20251124T153000Z
DTEND:20251124T170000Z
END:VEVENT
END:VCALENDAR