It was great to be part of this team effort across continents!

🚨New paper alert🚨 Delighted to share that our latest paper on predicting skin growth has just been published online in @SciReports congrats to Dr. Matt Nagle and the team! @abuganzat @michael_fop #DreamTeam 😜 https://t.co/LNKMV3u6gw

.@Minecraft, the best-selling video game in history, is now a teaching tool for solid mechanics! @PurdueME has published the mod and the pedagogy, so anyone can use it: https://t.co/T0YDvabXz6

We extend the framework to generate heterogeneous fields of material responses and solve finite element simulations on complex geometries.

Unlike traditional applications of diffusion models which work on discrete data, we generate samples of continuous representations of strain energy functions based on NODEs

How does diffusion work?

We use diffusion models which are the state-of-the-art for generative AI

We start with our polyconvex neural ordinary differential equations (NODE) to describe strain energy functions. How can we learn distribution of material responses?

🚨New #preprint 🚨 https://t.co/26fzsywAxk 'Generative hyperelasticity with physics-informed diffusion fields'! with @fcosahli @tajtac @ProfRausch @BilionisIlias We use diffusion for uncertainty quantification in material models. A 🧵👇

#EML_Webinar (Young Researchers Forum) on 17 October 2023 will be given by Emma Lejeune @LejeuneLab at Boston University @BU_Tweets via Zoom meeting Title: Data Driven Modeling of Mechanical Systems Discussion leader: Adrian Buganza Tepole @abuganzat, Purdue University

Please join the upcoming EML webinar given by Prof. Emma Lejeune on October 17, 2023. Zoom link: https://t.co/oAhojVfTLz @Mingchao_Liu @abuganzat @ToLiTeng

Go Vahid!!

iMechanica runs a Journal Club series, and for September I wrote an entry on some of the recent topics in soft tissue constitutive modeling. #AcademicTwitter #biomechanics #mechanics folks, what is on your mind? https://t.co/8UnkMao2n5

Our paper on data-driven viscoelasticity with Neural ODEs is published in Computer Methods in Applied Mechanics and Engineering! This news couldn't come at a better time because we are celebrating eid today. I will take this as CMAME's eid gift to me!

congrats!!!!!

Super excited to be part of this study!

We use neural ODEs to create data-driven potentials with build-in (poly)convexity in order to guarantee minimizers of the strain energy and positive energy dissipation a priori. Being data-driven, framework can capture: 🧠, 🫀,🩸-clot, 🛞... code: https://t.co/KfAqc5SNuf

New preprint work from the lab by @tajtac in collaboration with @fcosahli and @ProfRausch: Data-driven anisotropic finite viscoelasticity using neural ODEs https://t.co/PH1e8ap8bO #MachineLearning #DataScience

We developed challenges like building a bridge in the desert. Prof. Bill Watson and Alexander Bowman helped us frame the challenges within the Problem Based Learning (PBL) framework. If you want to use it in your class let me know! Or just use it for fun 😄4/4