AI/ML Conversations Meetup: When AI Beats Physics #NYTechWeek
Hosted by
◕‿◕
•‿•
◕‿◕•‿•0/50 spots left
AI/ML Conversations is a forum where data science and machine learning experts can showcase their work, fostering an environment where we can collectively discover better and safer applications for AI products!
Agenda:
5:30PM Doors open
5:30PM - 6:15PM Reception, networking
6:15PM - 7:15PM Piero Paialunga, Machine Learning Researcher at University Of Cincinnati "When AI Beats Physics: Surrogate Models That Make Simulations 1 Million × Faster"
7:15PM - 8:30PM Further Networking & get-together in the nearby bar.
!!! IMPORTANT !!!
- Please provide your full legal name at the time of RSVP, as it is necessary to enter the building and please ensure to bring a valid photo ID.
This event is hosted at the Capital One Office! Enter through 11 W 19th Street main entrance. Show your photo ID at the front desk and proceed to the 3rd floor.
Talk description:
Finite‑Element (FE) simulations are the gold standard for material and structural analysis. Nonetheless, as they are numerical solvers, they make the GPU sing for hours or days. In my talk, I'll show how physics‑informed deep‑learning (PiDL) surrogates cut those runtimes by 1 M×, incredibly efficiently. The session walks through: 1) building PiDL architectures that emulates differnetial equations, 2) training tricks for scarce label regimes, and 3) real‑world applications of surrogate models for crack detection and design optimization. Attendees will leave with code snippets, benchmarking data, and a mental model for deciding when AI can safely replace physics solvers. Attendees will walk away with practical examples, benchmark results, and a clear framework for judging when surrogate models provide real engineering value.
This event is a part of #NYTechWeek—a week of events hosted by VCs and startups to bring together the tech ecosystem. Learn more at www.tech-week.com.
Guest List
❛ᴗ❛
ᵔᴥᵔ
^⎵^