With NVIDIA Modulus and Niki Loppi, a talk event at Cineca on PINNs (Physics Informed Neural Networks)

Scientific research and Artificial Intelligence: around this broad theme, the EuroCC Italy talk event dedicated to Physics Informed Neural Networks (PINNs) will unfold, scheduled for Wednesday, June 5, at Cineca headquarters, from 2:00 PM to 4:00 PM.

During the event, we will have the opportunity to explore the transformative impact of Artificial Intelligence on scientific research, thanks to the intervention by Niki Loppi (PINNs expert) and with a specific focus on NVIDIA’s revolutionary Modulus framework. Modulus, with its innovative ability to use physics-informed neural networks to model parametrized physical systems, is opening new frontiers in the efficiency of scientific modeling.

The talk will last for 1 hour and 30 minutes. Afterwards, a Q&A session is scheduled. More information follows.

Talk on PINNs with Niki Loppi
Wednesdat, June 5th, 2:00 – 4:00 PM (CET)
Via Magnanelli, 6/3, Casalecchio di Reno (Bologna)

The Talk
This talk will delve into the transformative impact of AI on scientific research, highlighting NVIDIA’s Modulus framework. As a pioneering tool, Modulus utilizes physics-informed neural networks to model parametrized physical systems with cutting-edge efficiency. We will explore how this avant-garde technology is advancing scientific research, enabling researchers to tackle challenges previously considered insurmountable. Participants will gain insights into the future of AI-driven science, marked by the innovative applications of Modulus in various research fields.

Niki Loppi
Niki Loppi is an AI/HPC solutions architect at NVIDIA, helping academic researchers leverage NVIDIA’s technology stack through the NVIDIA AI Technology Center program. Before joining NVIDIA, he worked as a researcher in the Department of Aeronautics at Imperial College London, where he also obtained his PhD in Computational Fluid Dynamics. Specifically, his research focused on the development of high-order accurate numerical methods for solving large-scale incompressible fluid flow problems using massively parallel modern GPU architectures.

Registration
To participate in the event, registration is required at this link: https://forms.office.com/e/R0jnZPX5WD