Methods and apparatuses for designing optical systems using machine learning with delano diagrams
Methods and apparatuses for designing optical systems are provided. In this case, on a plurality of known optical systems, machine learning is carried out in order to train a computing device. After this training, the computing device can generate a design for an optical system on the basis of parameters describing desired properties of an optical system.
1. A method for designing optical systems, comprising:
providing a plurality of optical systems, and
carrying out a machine learning method on the basis of the plurality of optical systems,
wherein providing a plurality of optical systems comprises classifying the plurality of optical systems in order to provide parameters describing the plurality of optical systems,
wherein the classifying is carried out based on Delano diagrams of the plurality of optical systems, and
wherein the machine learning is carried out on the basis of the parameters obtained from the classifying based on the Delano diagrams being used as a feature vector for the machine learning.
2. The method of claim 1 , wherein carrying out the machine learning method comprises training an artificial neural network.
3. The method of claim 2 , wherein the neural network comprises a plurality of layers.
4. The method of claim 1 , wherein the parameters comprise first parameters describing components of the plurality of optical systems.
5. The method of claim 1 , wherein the parameters comprise second parameters describing optical properties of the plurality of optical systems.
6. The method of claim 1 , wherein the machine learning method comprises a reinforcement learning method.
7. The method of claim 1 , wherein providing the plurality of optical systems comprises designing the plurality of optical systems by an optical designer, wherein the machine learning method comprises a method of imitation learning on the basis of the designing.
8. The method of claim 1 , comprising:
feeding parameters describing desired properties after training an apparatus by said machine learning method, and
obtaining a design of an optical system by the apparatus.
9. The method of claim 8 , further comprising manufacturing an optical system according to the design.
10. The method of claim 1 , wherein the machine learning method comprises applying a metric based on the Delano diagrams.
11. A tangible storage medium comprising:
a computer program having a program code which, when executed on a processor, causes the processor to carry out a machine learning method on the basis of a plurality of provided optical systems,
wherein the machine learning method comprises classifying the plurality of optical systems in order to provide parameters describing the plurality of optical systems,
wherein the classifying is carried out based on Delano diagrams of the plurality of optical systems, and
wherein the machine learning is carried out on the basis of the parameters obtained from the classifying based on the Delano diagrams being used as a feature vector for the machine learning.
12. The storage medium of claim 11 , wherein the program code further causes the processor to classify the plurality of optical systems in order to provide parameters describing the plurality of optical systems, wherein the machine learning is carried out on the basis of the parameters.
13. An apparatus for designing optical systems, comprising:
a computing device configured to carry out machine learning on the basis of a plurality of optical systems to train the computing device,
wherein providing a plurality of optical systems comprises classifying the plurality of optical systems in order to provide parameters describing the plurality of optical systems,
wherein the classifying is carried out based on Delano diagrams of the plurality of optical systems, and
wherein the machine learning is carried out on the basis of the parameters obtained from the classifying based on the Delano diagrams being used as a feature vector for the machine learning.
14. The apparatus of claim 13 , wherein the apparatus is configured to classify the plurality of optical systems in order to provide parameters describing the plurality of optical systems, wherein the machine learning is carried out on the basis of the parameters.
15. The apparatus of claim 14 , wherein providing a plurality of optical systems comprises classifying the plurality of optical systems in order to provide parameters describing the plurality of optical systems, wherein the machine learning is carried out on the basis of the parameters.
16. The apparatus of claim 14 , wherein the parameters comprise first parameters describing components of the plurality of optical systems.
17. The apparatus of claim 13 , wherein the computing device is configured to provide a design of an optical system based on parameters describing desired properties of the system and based on the training.