DOI | Resolve DOI: https://doi.org/10.1109/PN50013.2020.9166993 |
---|
Author | Search for: Xu, Dan-Xia1; Search for: Melati, Daniele1; Search for: Kamandar Dezfouli, M.1; Search for: Schmid, Jens H.1; Search for: Cheben, Pavel1; Search for: Cheriton, Ross1; Search for: Janz, Siegfried1; Search for: Grinberg, Yuri2; Search for: Niegemann, Jens; Search for: Pond, James; Search for: Reid, Adam |
---|
Affiliation | - National Research Council of Canada. Advanced Electronics and Photonics
- National Research Council of Canada. Digital Technologies
|
---|
Format | Text, Article |
---|
Conference | 2020 Photonics North (PN), May 26-28, 2020, Niagara Falls, Ontario |
---|
Physical description | 1 p. |
---|
Subject | nanophotonics; silicon photonics; optimization; machine learning; pattern recognition; principal component analysis (PCA); dimensionality reduction; inverse design |
---|
Abstract | The optimization of complex high-dimensional photonic structures is often limited by computational resources. Current techniques based on global optimization algorithms or shape/topology inverse design treat design variables as entirely independent. However, there is often correlation between the input variables and patterns in the design outcomes. We review our strategy of using machine learning pattern recognition for building the performance map of a high-dimensional design space, thereby quickly guiding the search to a small region of interest and significantly improving the computational efficiency. This strategy is found beneficial in both forward and inverse design process flow. |
---|
Publication date | 2020-08-17 |
---|
Publisher | IEEE |
---|
In | |
---|
Series | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 9d9404b9-7fbf-4d34-937d-b5abeb4d8fcb |
---|
Record created | 2021-07-21 |
---|
Record modified | 2021-07-23 |
---|