IEEE Photonics Society

Boston Photonics Society Chapter

Boston Chapter of the IEEE Photonics Society

Machine Learning and Optical Systems PDF

Wednesday, October 7, 14, 21, 28 and November 4, 2020, 7:00-9:30 PM
Located at Online Seminar

Wednesday
October 14, 2020
8:15 PM
 

Add to Calendar Add to Calendar

Interfacing Photonics with Artificial Intelligence: A New Design Strategy for Photonic Metamaterials based on Deep Learning

Prof. Yongmin Liu, Northeastern University, Boston, MA

 

Prof. Yongmin Liu, Northeastern University, Boston, MA

Abstract:  Over the past decades, we have witnessed tremendous progress and success of photonic metamaterials. By tailoring the geometry of the building blocks of metamaterials and engineering their spatial distribution, we can control the amplitude, polarization state, phase and trajectory of light in an almost arbitrary manner. However, the conventional physics- or rule-based approaches are insufficient for designing multi-functional and multi-dimensional metamaterials, since the degrees of freedom in the design space become extremely large. Deep learning, a subset of machine learning that learns multilevel abstraction of data using hierarchically structured layers, could potentially accelerate the development of complex metamaterials with high efficiency, accuracy and fidelity. In the first part of my talk, I will present a new concept of chiral metamirrors, which can achieve near-perfect reflection of designated circularly polarized light without reversing its handedness, yet complete absorption of the other polarization state [1]. Such a metamaterial can be used for polarimetric imaging to extract the polarization information of light [2]. In the second part of my talk, I will discuss our recent effort in applying deep learning to simultaneously realize the forward prediction and inverse design of 2D and 3D metamaterials that exhibit pronounced chiral or anisotropic responses [3,4]. Our results show that deep learning, as a data-driven approach, can help to unveil the highly nonintuitive and nonlinear structure-property relationship in metamaterials. Deep learning and other artificial intelligence techniques are currently transforming the areas of optical design, integration and measurement. More transformative advancements are anticipated as researchers with different background continuously contribute to the emerging field where photonics and artificial intelligence merge.


References: [1] Z. J. Wang et al., 'Circular Dichroism Metamirrors with Near-Perfect Extinction', ACS Photonics 3, 2096 (2016). [2] L. Kang et al., 'Preserving Spin States upon Reflection: Linear and Nonlinear Responses of a Chiral Meta-Mirror', Nano Letters 17, 7102 (2017). [3] W. Ma et al., 'Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials', ACS Nano 12, 6326 (2018). Research Highlight in Nature Photonics 12, 443 (2018). [4] W. Ma et al., ' Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy', Advanced Materials 31, 1901111 (2019).

 

Biography:  Dr. Yongmin Liu obtained his Ph.D. from the University of California, Berkeley in 2009. He joined the faculty of Northeastern University at Boston in fall 2012, and currently he is an associate professor in the Department of Mechanical & Industrial Engineering and the Department of Electrical & Computer Engineering. Dr. Liu’s research interests include nano optics, nanoscale materials and engineering, plasmonics, metamaterials, biophotonics, and nano optomechanics. He has authored and co-authored more than 80 journal papers, including Science, Nature, Nature Nanotechnology, Nature Communications, Advanced Materials, Physical Review Letters and Nano Letters. Dr. Liu was a recipient of the Faculty Fellow of College of Engineering at Northeastern University (2019), NSF CAREER Award (2017), Office of Naval Research Young Investigator Award (2016), SPIE DCS Rising Researcher Award (2016), 3M Non-Tenured Faculty Award (2016), Air Force Summer Faculty Fellowship (2015), and Chinese Government Award for Outstanding Students Abroad (2009). Currently he serves as an editorial board member for Scientific Reports, Nano Convergence, EPJ Applied Metamaterials.

 

The workshop expenses have
been generously supported by:

 

MERL


For more information on the technical content of the workshop, contact either:
1) Keisuke Kojima, (kojima@merl.com), Chair
2) Ajay Garg, (ajay.sinclair.garg@ieee.org), Co-Chair
3) Dean Tsang, (tsang@ieee.org), Co-Chair
4) Bill Nelson, (w.nelson@ieee.org), Co-Chair