Ai Ping Yow,1 Yueqian Zhang,2 Christoph Menke,2 Ralf Wolleschensky,3 Damon Wong,4,5 Peter Török1
1Institute for Digital Molecular Analytics and Science (Singapore) 2Carl Zeiss AG (Germany) 3Carl Zeiss Microscopy GmbH (Germany) 4Singapore Eye Research Institute (Singapore) 5Singapore National Eye Ctr. (Singapore)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
In this study, we have used the policy-gradient based reinforcement learning approach to generate initial design for microscope objective lenses. The lens parameters within the defined ranges can be determined by the model based on the given specifications. The results obtained from our analysis suggest that the reinforcement learning model can generate appropriate starting points which expedite the convergence of the optimisation process.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Ai Ping Yow, Yueqian Zhang, Christoph Menke, Ralf Wolleschensky, Damon Wong, Peter Török, "Microscope objective lens design generation with reinforcement learning," Proc. SPIE 13019, Optical Design and Engineering IX, 130191H (18 June 2024); https://doi.org/10.1117/12.3011969