MétaCan
Menu
Back to cohort
Record W4399725055 · doi:10.1117/12.3025345

Future of optical system and lens design in the AI era

2024· article· en· W4399725055 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicAdvanced optical system design
Canadian institutionsUniversité Laval
Fundersnot available
KeywordsComputer scienceContext (archaeology)Presentation (obstetrics)Task (project management)WonderObject (grammar)Artificial intelligenceField (mathematics)Deep learningData scienceHuman–computer interactionSystems engineeringEngineering

Abstract

fetched live from OpenAlex

The arrival of ChatGPT, Google Bard, and other highly advanced artificial intelligence model show us just how brilliantly tasks can be reproduced by those engines. So, it's legitimate to wonder how our field (or any fields) might be affected in the future. We've already seen the beginnings of the possibilities, notably with LensNet [1], which provides optical designers with starting points for common cases; we can also study a solution space of certain type of lenses using deep learning [2]; and more recently, papers on the use of deep learning to simulate the entire chain of an optical system from object to final image processing, including tasks such as recognition. These latest end-to-end simulations have shown that in some cases, it is even necessary to redefine the optical optimization criteria to maximize certain computer tasks. In short, the computer doesn't necessarily need a good image in terms of MTF to perform its task. In this context, how the future will be affected or enhanced by these new AI approaches. In this presentation, I will first give a brief history of how AI has impacted optical system design since 40 years. Then I will use examples to discuss the extraordinary acceleration in works over the past 5 years, the choices that have or haven't been made, and the importance of having access to source code from publications. Finally, I will conclude with some thoughts on what may or may not lie ahead, and how we can introduce these new technologies into the training of future optical system designers. [1] Geoffroi Côté, Jean-François Lalonde, and Simon Thibault, "Deep learning-enabled framework for automatic lens design starting point generation," Opt. Express 29, 3841-3854 (2021). [2] Geoffroi Côté, Yueqian Zhang, Christoph Menke, Jean-François Lalonde, and Simon Thibault, "Inferring the solution space of microscope objective lenses using deep learning," Opt. Express 30, 6531-6545 (2022).

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.983
Threshold uncertainty score0.193

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.012
GPT teacher head0.223
Teacher spread0.210 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced optical system designFrench-language works237,207