Taught In:
company training
Levels:
Level of expertise and familiarity the material in this course assumes you have. The greater the amount of introductory material taught in the course, the less you will need to be familiar with when learner attend.
Participants:
The course is beneficially to anyone working in materials or an industry that builds on a material interaction platform. Those are like Pharmaceuticals, Regenerative Medicine, Energy, or Materials Engineering, who is interested in understanding how to optimize a material’s structure and performance. In addition also to profession like lead scientists, software engineers, technology outreach directors, sustainability directors, technical leaders, entrepreneurs, founders, investors, creatives and science communicators, and policymakers/influences who wants/needs of new opportunities in material design.
Also, participants will get expected to review a carefully curated collection of readings and vides in preparation for the course. Those materials will help maximize your experience. In support, participants will have the chance to complete a pre-course survey to help the instructors/guidance identify common interests and challenges participants want to solve in the machine learning clinic.
Course Overview:
Today, an engineer or scientist can simply enter the desired properties into a computer program and the system will manufacture a microstructure with those specifications. Algorithms can be used to predict which chemical building blocks can be combined to create advanced materials with superior functions, from ultra-strong, lightweight materials used in the automotive, construction, and aerospace industries, to biomaterials used in implants and biomedical devices with the ability to self-heal and regenerate.
In this course, participants will enhance your ability to leverage materials design, machine learning, and additive manufacturing to create better materials, with emphasis on four of the most-in demand areas of materials engineering. First is computational modeling, from molecular dynamics, multi-scale methods, to the high-throughput experimental data collection and analysis. Second is biomaterials and bio-inspiration from proteins, natural composites, smart and tunable materials, to biomass engineering. Third is the machine learning & computing, from material informatics and AI/ML applications in materials modeling, design and manufacturing, include the data set generation. Last and not least an additive manufacturing as manufacturing designers material like composites.
Indicate alongside learners from around the world, participants will gain insights into the science, technology, and state-of-the-art computing methods being used to fabricate innovative materials from the molecular scale upwards. Through lectures and hands-on labs and clinics, you will learn how to construct, in a bottom-up manner, atomically precise products through the use of molecular design, predictive modeling, and manufacturing, allowing the fabrication of a vast array of advanced, innovative designs for a wide-range of applications. You will also learn how to access and utilize web-based machine learning tools for materials analysis, and cement your knowledge with a “from design to production” project, in which you will use AI and other computational methods to produce a custom 3D-printed smart material.
In short, in this condensed course, learner will participate in hands-on clinics and labs designed to help you optimize your smart material design and manufacturing through the use of large-scale computational modeling, material informatics, and artificial intelligence/machine learning. Therefore, join the cutting-edge of intelligent material design and discover how to integrate advanced technologies to drive the development of next-generation smart materials.
Methods:
The course is taught from traditional classroom lectures and riveting discussions to group projects to engaging and interactive simulations and exercises with your peers. An interactions by demonstrations, experiments and simulations itself.
Outcomes:
The fundamentals of Multi-scale Materials Designs.
- Master cutting-edge computational tools that range from multi-scale modeling to machine learning and artificial intelligence.
- The use of design tools to predict mechanical properties.
- Utilize cloud computing to design novel designer proteins and superior material properties.
- Synthesize computationally designed hierarchical composites using advanced manufacturing techniques.
- Design and general novel materials in a computational-manufacturing pipeline.
- Evaluate and apply computational tools in materials design.
- Explore fundamentals and codes for performing state-of-the-art techniques.
Topic Outline:
Lec 01 – Basic Methods and Applications in Computational Material Science
Lec 02 – Introduction to Materials Informatics and AI/ML
Lec 03 – Introduction to Machine Learning Clinic
Lec 04 – Printing Lab
Lec 05 – Class Design Studio
Lec 06 – Additive manufacturing of multi-material optimize materials
Lec 07 – Molecular modeling, design, and data visualization lab
Lec 08 – Interactive case studies
—— participant presentations & group work time
Lec 09 – Advanced modeling methods
Lec 10 – Advanced machine learning methods (auto-encoders, NLP, transformer, game theory/GANs, graph neural networks, and geometric deep learning)
Lec 11 – Machine Learning Clinic
Lec 12 – Hands-on Learning Exercises
Lec 13 – Interactive Design visualization and materials processing lab
Lec 14 – Extreme material performance & failure case study
Lec 15 – Experimental data collection, high-throughput approaches, and dataset curation
Lec 16 – Theory Model Demonstration and Bio-Transfer
Lec 17 – Machine Learning Clinic II
Lec 18 – Computational Experimental Methods (cloud computing, neural modeling, Bayesian process optimization)
Lec 19 – Advanced computational methods (GPU computing, quantum computing, neuromorphic computing)
Lec 20 – Big data and analytics
Lec 21 – Printed smart material case study