# Automated AI for Adapting to New Data Without Retraining > This patent describes an automated system that builds artificial intelligence models capable of adapting to new, different data without needing full retraining, by learning to ignore irrelevant changes. - **Patent:** US 20230162023 - **Original title:** System and Method for Automated Transfer Learning with Domain Disentanglement - **Owner:** Mitsubishi Electric Research Laboratories - **Status:** Active - **Times cited:** 46 - **Field:** ai_ml, software, automotive, consumer_electronics, telecommunications ## What it does This system automatically builds artificial neural network architectures. It uses interfaces to receive training, validation, and testing data, which includes 'task labels Y' (what the AI needs to identify) and 'nuisance variations S' (irrelevant changes, like lighting or background). Memory banks store 'reconfigurable deep neural network (DNN) blocks' and settings called 'hyperparameters'. A processor then explores different hyperparameters and methods, including 'auxiliary regularization modules', to adjust how the DNN blocks work. The goal is to make the AI's predictions 'insensitive to the nuisance variations S', meaning it can identify the task labels accurately even when the irrelevant parts of the data change. For example, an AI trained to recognize a specific object in bright light could still recognize it in dim light without needing to be fully retrained. ## What it does NOT cover - Does not cover manually designed neural network architectures for transfer learning, as it specifies 'automated construction'. - Does not cover transfer learning methods that do not explicitly disentangle latent variables from nuisance variations using auxiliary regularization modules. - Does not cover systems that do not explore hyperparameters of regularization, pre-processing, or post-processing methods to achieve nuisance robustness. - Does not cover non-deep neural network (DNN) architectures, as it specifically references 'reconfigurable deep neural network (DNN) blocks'. - Does not cover methods that do not aim for 'nuisance-robust Bayesian inference' to handle domain shifts. ## The clever bit The innovation lies in automatically exploring and configuring neural network components and methods to actively 'disentangle' important features from irrelevant 'nuisance variations'. This allows the AI to learn what truly matters for a task, making it highly adaptable and robust when encountering new, slightly different data environments. ## Real-world examples 1. Autonomous vehicle perception systems adapting to different weather or lighting conditions 2. Medical image analysis systems working across various scanner types or patient demographics 3. Industrial inspection systems identifying defects on different production lines 4. Speech recognition systems handling varying background noise or speaker accents ## Why it matters AI models often struggle when deployed in real-world situations where data differs slightly from their training data, a problem known as 'domain shift'. This patent offers a way to automatically build AI models that are robust to these changes, making them more reliable and reducing the need for expensive, time-consuming retraining. This is crucial for deploying AI in diverse environments, from self-driving cars encountering varied weather to medical imaging systems used in different hospitals. ## Frequently asked questions ### What does Automated AI for Adapting to New Data Without Retraining cover? This patent describes an automated system that builds artificial intelligence models capable of adapting to new, different data without needing full retraining, by learning to ignore irrelevant changes. ### Who owns patent US 20230162023? This patent is owned by Mitsubishi Electric Research Laboratories. ### When does this patent expire? This patent is expected to expire on February 1, 2042, when the invention enters the public domain. ### What is patent US 20230162023 cited by? This patent has been cited by 46 later patents that build on its ideas. ### What problem does this patent solve? AI models often struggle when deployed in real-world situations where data differs slightly from their training data, a problem known as 'domain shift'. This patent offers a way to automatically build AI models that are robust to these changes, making them more reliable and reducing the need for expensive, time-consuming retraining. This is crucial for deploying AI in diverse environments, from self-driving cars encountering varied weather to medical imaging systems used in different hospitals. ### What does this patent NOT cover? Does not cover manually designed neural network architectures for transfer learning, as it specifies 'automated construction'. **Full plain-English explainer:** https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement **Original patent:** https://patents.google.com/patent/US20230162023 --- _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 Learns New Tasks Using Old Data Labels](https://patentbrief.org/patent/us/11062228/gpt-3-few-shot-learning) — A method for helping AI models understand new topics by grouping similar labels from different datasets into a shared, broader category. - [How to Automatically Tune Machine Learning Settings Using Smart Math](https://patentbrief.org/patent/us/11501192/alphafold-protein-structure-prediction) — A system that uses advanced statistical modeling to automatically find the best settings for complex machine learning models, saving engineers from manual trial and error. - [How AI Automatically Labels Images and Checks Its Own Work](https://patentbrief.org/patent/us/11023780/siri-on-device-speech-recognition) — A method for training AI to label images by calculating how uncertain it is about its own predictions, allowing it to verify its accuracy without human help. - [Training AI Models Across Different Computers](https://patentbrief.org/patent/us/12574477/distributed-deep-learning-using-a-distributed-deep-neural-network) — This 2026 patent describes a way to train AI models on one computer, send a version to another computer for further training with private data, and then update the original model with the improvements. - [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.