Machine Learning (ML) and artificial intelligence (AI) have been transformative in areas of chemistry and materials in which large datasets have or can be generated. However, when data is scarce and expensive, as is the case for biomaterials design, computational modeling has been limited. Computer-aided design of biomaterials often relies on ab initio modeling (e.g., molecular dynamics), which require no data but cannot predict complex properties such as biomaterial mechanics, optical properties, or in vitro or in vivo behavior or efficacy. Thus, human intuition coupled with experimental trial and error is often state-of-the-art for design of new biomaterials. These conventional approaches to develop biomaterials are expensive and laborious and have significantly slowed the translation of new biomedical devices into clinical practice. To address this hurdle, innovative approaches include the use of ML and AI design with a long-term goal of a (bio)materials genome. This webinar will overview the broader field of ML and AI and how advances in computational power coupled with big data analysis and innovations in machine learning, modeling, and simulation are enabling artificial intelligence to revolutionize biomaterials design and development.
- Moderator: Danielle Benoit, University of Rochester
- Moderator: Andrew White, University of Rochester
- Payal Das, AI Science, Thomas J. Watson Research Center, IBM Research
- Tomohiro Hayashi, Tokyo Institute of Technology
- Debora Marks, Blavatnik Institute of Systems Biology, Harvard Medical School
- Andrew White, University of Rochester
Click here to register.
*There is a cost for this webinar. Please see the registration site for more details.*