Machine Learning for Metamaterial Design
Brief Description of Project:
Metamaterials are artificially structured materials that can exhibit exotic optical properties such as high frequency magnetism and a negative index of refraction. The structure of the metamaterial unit cell dictates its response and while there are guiding principles for design these principles are insufficient when functionality becomes more complex. The purpose of this summer research experience is to investigate different machine learning (ML) algorithms and techniques and implement one of them for metamaterial design. The student’s ML code will be benchmarked against traditional design techniques to determine the efficacy of their approach. If time permits, the student will have a chance to use their code to design metamaterials functions that cannot be achieved using traditional design techniques.
This project is best suited for individuals with interests in computer science and machine learning. Experience with numerical modeling is also beneficial. No experience is needed in metamaterial design.
Nature of Supervision:
The student will work closely with Prof. Valentine and a graduate student on this project.
A Brief Research Plan (period is for 10 weeks):
Weeks [1–3]: The student will familiarize themselves with ML techniques.
Weeks [3-8]: The student will implement an ML technique for metamaterial design.
Weeks [8-10] The student will benchmark their code against traditional design techniques.
Number of Open Slots: 1
Name: Jason Valentine
Department: Electrical Engineering and Computer Science