# How an AI Learns to Recognize Objects by Generating Its Own Examples > This patent describes an enhanced artificial intelligence system that uses two competing networks, a generator and a discriminator, with special 'capsule layers' to create and recognize specific types of data, like images, even with limited initial examples. - **Patent:** US 12154036 - **Original title:** Enhanced generative adversarial network and target sample recognition method - **Owner:** Shenzhen Institutes of Advanced Technology - **Granted:** 2024 - **Status:** Active - **Times cited:** 1 - **Field:** ai_ml, software, telecommunications, consumer_electronics ## What it does This patent details an 'enhanced generative adversarial network' (GAN) and a method for recognizing specific 'target samples.' The system includes at least one 'enhanced generator' that creates new data from initial data, and at least one 'enhanced discriminator' that evaluates this generated data. The discriminator then provides feedback to the generator, helping it improve. A key feature of this enhanced discriminator, as described in claim 1, is its structure: a 'convolution layer,' a 'basic capsule layer,' a 'convolution capsule layer,' and a 'classification capsule layer,' all connected in sequence. The number and setup of these layers can be adjusted based on the specific features of the 'target sample' being recognized. For example, to recognize a rare type of medical image, the system could generate many synthetic versions of that image, and the discriminator, with its capsule layers, would learn to distinguish them from other images, even if only a few real examples exist. ## What it does NOT cover - Does not cover generative adversarial networks that do not include capsule layers within their discriminator component. - Does not cover target sample recognition methods that do not use an enhanced generative adversarial network with the specified discriminator architecture. - Does not cover GANs where the discriminator's convolution, basic capsule, convolution capsule, and classification capsule layers are not sequentially connected. - Does not cover systems where the quantities and structure parameters of the discriminator's specific layers are not set according to the target sample's features. ## The clever bit The truly clever part is the integration of capsule networks directly into the discriminator of a GAN. While GANs are good at generating and distinguishing data, capsule networks excel at understanding hierarchical relationships and orientations of features, allowing the discriminator to learn more robust and invariant representations of 'target samples' than traditional convolutional neural networks. ## Real-world examples 1. Advanced medical image analysis for disease detection 2. High-fidelity synthetic data generation for training AI models 3. Facial recognition systems that need to identify faces from various angles 4. Quality control systems for manufacturing that detect subtle defects 5. Autonomous vehicle perception systems for recognizing specific objects ## Why it matters Generative Adversarial Networks (GANs) are a powerful class of artificial intelligence models used for generating realistic data, like images, audio, or text. This patent enhances the discriminator part of a GAN by incorporating 'capsule layers,' which are known for better understanding spatial relationships and orientations in data, especially images. This improvement could lead to more robust and accurate recognition systems, particularly in fields where data is scarce or complex, such as medical diagnostics or specialized object detection. ## Frequently asked questions ### What does How an AI Learns to Recognize Objects by Generating Its Own Examples cover? This patent describes an enhanced artificial intelligence system that uses two competing networks, a generator and a discriminator, with special 'capsule layers' to create and recognize specific types of data, like images, even with limited initial examples. ### Who owns patent US 12154036? Shenzhen Institutes of Advanced Technology owns this patent, granted in 2024. ### When does this patent expire? This patent is expected to expire on August 21, 2040, when the invention enters the public domain. ### What is patent US 12154036 cited by? This patent has been cited by 1 later patents that build on its ideas. ### What problem does this patent solve? Generative Adversarial Networks (GANs) are a powerful class of artificial intelligence models used for generating realistic data, like images, audio, or text. This patent enhances the discriminator part of a GAN by incorporating 'capsule layers,' which are known for better understanding spatial relationships and orientations in data, especially images. This improvement could lead to more robust and accurate recognition systems, particularly in fields where data is scarce or complex, such as medical diagnostics or specialized object detection. ### What does this patent NOT cover? Does not cover generative adversarial networks that do not include capsule layers within their discriminator component. **Full plain-English explainer:** https://patentbrief.org/patent/us/12154036/enhanced-generative-adversarial-network-and-target-sample-recognition-method **Original patent:** https://patents.google.com/patent/US12154036 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How AI Generates Images Based on Style and Content Cues](https://patentbrief.org/patent/us/12141700/generative-adversarial-network-for-generating-images) — This patent describes an artificial intelligence system that creates new images by understanding both what the image should show (like a cat) and how it should look (like a high-quality photo), using a special internal layer to blend these instructions. - [How to Train AI Models with Fake Data Using Generative Networks](https://patentbrief.org/patent/us/20230297446/data-model-generation-using-generative-adversarial-networks) — This patent describes a method for training artificial intelligence models using specially generated fake, or 'synthetic,' data created by a generative adversarial network, ensuring the synthetic data is high-quality and safe for training. - [AI Method for Sharpening Low-Dose PET Scans with Multi-Task Learning](https://patentbrief.org/patent/us/11756161/method-and-system-for-generating-multi-task-learning-type-generative-adversarial) — This patent describes an AI method using a special type of neural network called a multi-task learning generative adversarial network (GAN) to improve the quality of medical images from low-dose PET scans, making them look like standard-dose scans. - [Improving Medical Image Segmentation with AI and Fake Data](https://patentbrief.org/patent/us/11580646/medical-image-segmentation-method-based-on-u-net) — This patent describes a method to make AI better at finding specific things in medical images, like tumors, by using computer-generated fake images to train the AI and a special network design. - [Sharing AI Knowledge Between Private Datasets Using Synthetic Data](https://patentbrief.org/patent/us/12039012/systems-and-methods-for-heterogeneous-federated-transfer-learning) — This patent describes a method for two separate AI systems to share learned information by generating artificial data based on common features, without directly exchanging their private training data.