Introduction to Deep Learning for Materials Design

Born out of the research labs of TU Delft with over 20 years of experience in the synthesis of aerosols, VSPARTICLE believes there is a whole new world of possibilities at the nanoscale.As we all start to understand these possibilities, it will enable research and industry to rethink production processes and develop new materials to create innovative applications. At VSPARTICLE we support this process by making nanoparticle-based manufacturing as easy as pushing a button and providing research and industry with the tools to rapidly advance the field of nanotechnology.

VSPARTICLE B.V.

Intermediate-level workshop on deep learning applications in materials design.

This workshop is organised as a collaboration between <a href="https://materialpioneers.com/" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">Material Pioneers</a>,<a href="https://osc-delft.github.io/" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer"> Open Science Community Delft</a> and <a href="https://data.4tu.nl/info/en/" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">4TU.ResearchData</a> .We are at the beginning of an exciting era in which the design and modeling of materials and structures are accelerated by big data and advances in machine learning (ML) strategies. Contrary to traditional approaches based on trial-and-error/exhaustive simulations and experiments, ML methods exploit large data sets to identify otherwise unknown relations, thus creating efficient and invertible design-property maps. This enables a quick identification and reduction of the design space, eventually leading to a faster turnaround of material design by demand. In this light, this workshop will provide a brief introduction to ML for accelerating materials design. Specifically, the workshop will cover the basics and implementation of deep neural networks (a type of ML method), followed by application to a real-life materials design problem.InstructorSid Kumar is an Assistant Professor at TU Delft in the Department of Material Science and Engineering (Faculty-3mE). He obtained his Ph.D. in Aeronautics from Caltech in 2019 followed by a postdoc position at ETH Zürich. Previously, he obtained a dual M.S. in 2017 from Caltech in Aeronautics and Ecole Polytechnique (France) in Multiscale and Multiphysics Modeling, and a B.Tech. in Mechanical Engineering from IIT Delhi in 2014. He received the Foster and Coco Stanback fellowship in Engineering and Applied Science at Caltech and the University of Paris Saclay fellowship at Ecole Polytechnique. His current research interests lie at the intersection of mechanics of materials, computational modeling, and machine learning — with a focus on inverse problems in (meta-)material design and modeling.Website:https://www.mech-mat.comWho: The workshop is aimed at Early Career Reseachers (PhD candidates, postdocs and assistant professors/research associates) doing research in material science.Prerequisites:Participants should be familiar with using Python and Jupyter Notebooks. Some experience with Numpy/Pandas would be preferred, but not required.Where: This training will take place online. The organisers will provide you with the information you will need to connect to this meeting.For additional info, reach out to a.soro@vsparticle.com.

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Introduction to Deep Learning for Materials Design

Still looking for the right event?

Explore all online events to browse and filter by date, category, and more.

Introduction to Deep Learning for Materials Design

More Science & Tech events

Browse more Science & Tech events with different dates, prices, and formats to find your next great experience.

Still looking for the right event?

Explore all online events to browse and filter by date, category, and more.