Generative tandem neural network for optimization of nanophotonic color splitters
Bibliographic record
Abstract
Abstract Tandem neural networks have seen success in the inverse design of nanophotonic structures. However, unlike other generative inverse design approaches, these networks typically suffer from a significant limitation as they are single input single output networks with zero diversity. To address this limitation we propose a novel single input, multiple output tandem network specifically for the inverse design of color splitter nanophotonic structures. The color splitters can separate and redirect different colors of light into spatially separated pixels, thereby replacing the color filters used in digital cameras to mitigate absorptive losses. We additionally combine iterative transfer learning approaches to allow training on a small dataset of higher quality samples created through topology optimization, with the training based on a labeled dataset of just 128 labelled samples. The forward network is shown to work well in both interpolation and extrapolation, while a deficiency in the performance of the inverse network in extrapolation can be overcome by use of an additional genetic algorithm optimization. Overall, the tandem network combined with genetic optimization allows significant improvement in the performance of the nanophotonic structures, even compared to traditional gradient-based topology optimization. This technique promises more effective and resource-efficient approach at general optimization, marking a significant advance in the algorithmic design of nanophotonic devices.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".