17973188. INVERSE DESIGN SYSTEM DESIGNING NANO-OPTICAL DEVICE USING CONTROLLABLE GENERATIVE ADVERSARIAL NETWORK AND TRAINING AND DESIGN METHODS simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
- 1 INVERSE DESIGN SYSTEM DESIGNING NANO-OPTICAL DEVICE USING CONTROLLABLE GENERATIVE ADVERSARIAL NETWORK AND TRAINING AND DESIGN METHODS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 INVERSE DESIGN SYSTEM DESIGNING NANO-OPTICAL DEVICE USING CONTROLLABLE GENERATIVE ADVERSARIAL NETWORK AND TRAINING AND DESIGN METHODS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
INVERSE DESIGN SYSTEM DESIGNING NANO-OPTICAL DEVICE USING CONTROLLABLE GENERATIVE ADVERSARIAL NETWORK AND TRAINING AND DESIGN METHODS
Organization Name
Inventor(s)
INVERSE DESIGN SYSTEM DESIGNING NANO-OPTICAL DEVICE USING CONTROLLABLE GENERATIVE ADVERSARIAL NETWORK AND TRAINING AND DESIGN METHODS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17973188 titled 'INVERSE DESIGN SYSTEM DESIGNING NANO-OPTICAL DEVICE USING CONTROLLABLE GENERATIVE ADVERSARIAL NETWORK AND TRAINING AND DESIGN METHODS
Simplified Explanation
The abstract describes an inverse design system for designing a pattern of a structure in an image sensor. The system uses a controllable Generative Adversarial Network (cGAN) to generate an image of the structure based on a target characteristic. The cGAN includes a generator, a discriminator, and a classifier.
- The system uses a cGAN to design a pattern of a structure in an image sensor.
- The cGAN includes a generator that generates a fake image of the structure.
- A discriminator is used to determine whether the fake image is fake or real.
- A classifier is used to classify a class label associated with the fake image and corresponding to the target characteristic.
Potential Applications
- Designing patterns for image sensors.
- Creating customized structures for various applications.
- Generating images based on specific characteristics or features.
Problems Solved
- Traditional design methods for image sensors may be time-consuming and require manual intervention.
- Designing structures with specific characteristics can be challenging and may require expertise.
- Generating images based on target characteristics can be complex and may require extensive computational resources.
Benefits
- The inverse design system automates the process of designing patterns for image sensors.
- The use of a cGAN allows for the generation of images based on specific target characteristics.
- The system reduces the need for manual intervention and expertise in designing structures.
- The generated images can be used for various applications, including customized designs.
Original Abstract Submitted
An inverse design system is configured to design a pattern of a structure in an image sensor. The inverse design system may include; a CPU, a RAM loading a controllable Generative Adversarial Network (cGAN), wherein the cGAN is executable by the CPU to generate an image of the structure corresponding to a target characteristic, and an I/O interface receiving a training data set used to train the cGAN, communicating the training data set to the CPU, and outputting the image generated by the cGAN. The cGAN includes a generator generating a fake image of the structure, a discriminator determining whether the fake image is fake or real, and a classifier classifying a class label associated with the fake image and corresponding to the target characteristic.