{
  "patent_number": "US 20230162023",
  "country": "US",
  "title": "Automated AI for Adapting to New Data Without Retraining",
  "original_title": "System and Method for Automated Transfer Learning with Domain Disentanglement",
  "summary": "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.",
  "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."
  ],
  "filed": "2022-02-01",
  "granted": null,
  "expires": "2042-02-01",
  "status": "active",
  "holder": "Mitsubishi Electric Research Laboratories",
  "holder_url": "https://patentbrief.org/company/mitsubishi-electric-research-laboratories",
  "inventors": [
    {
      "name": "Toshiaki Koike Akino",
      "url": "https://patentbrief.org/inventor/toshiaki-koike-akino"
    },
    {
      "name": "Niklas Smedemark-Margulies",
      "url": "https://patentbrief.org/inventor/niklas-smedemark-margulies"
    },
    {
      "name": "Ye Wang",
      "url": "https://patentbrief.org/inventor/ye-wang"
    }
  ],
  "times_cited": 46,
  "tags": [
    "ai_ml",
    "software",
    "automotive",
    "consumer_electronics",
    "telecommunications"
  ],
  "abstract": "A system and method for automated construction of an artificial neural network architecture are provided. The system includes a set of interfaces and data links configured to receive and send signals, wherein the signals include datasets of training data, validation data and testing data, wherein the signals include a set of random number factors in multi-dimensional signals, wherein part of the random number factors are associated with task labels to identify, and nuisance variations. The system further includes a set of memory banks to store a set of reconfigurable deep neural network (DNN) blocks, hyperparameters, trainable variables, intermediate neuron signals, and temporary computation values including forward-pass signals and backward-pass gradients. The system further includes at least one processor, in connection with the interface and the memory banks, configured to submit the signals and the datasets into the reconfigurable DNN blocks, wherein the at least one processor is configured to explore hyperparameters of regularization modules, pre-processing and post-processing methods such that the reconfigurable DNN blocks achieve nuisance-robust Bayesian inference to be transferable to new datasets with domain shifts.",
  "url": "https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement",
  "markdown_url": "https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement/md",
  "google_patents_url": "https://patents.google.com/patent/US20230162023",
  "relatedPatents": [
    {
      "patentNumber": "12574477",
      "countryCode": "US",
      "title": "Training AI Models Across Different Computers",
      "url": "https://patentbrief.org/patent/us/12574477/distributed-deep-learning-using-a-distributed-deep-neural-network"
    },
    {
      "patentNumber": "10599957",
      "countryCode": "US",
      "title": "How to Automatically Detect and Fix Changes in AI Model Data",
      "url": "https://patentbrief.org/patent/us/10599957/systems-and-methods-for-detecting-data-drift-for-data-used-in-machine-learning-m"
    },
    {
      "patentNumber": "12423586",
      "countryCode": "US",
      "title": "Making AI Smarter by Focusing on Unsure 'Nodes'",
      "url": "https://patentbrief.org/patent/us/12423586/training-nodes-of-a-neural-network-to-be-decisive"
    },
    {
      "patentNumber": "12518214",
      "countryCode": "US",
      "title": "Training AI on Private Data Without Seeing It",
      "url": "https://patentbrief.org/patent/us/12518214/distributed-machine-learning-systems-including-generation-of-synthetic-data"
    },
    {
      "patentNumber": "9965705",
      "countryCode": "US",
      "title": "How AI Uses Question-Guided Attention to Answer Questions About Images",
      "url": "https://patentbrief.org/patent/us/9965705/systems-and-methods-for-attention-based-configurable-convolutional-neural-networks-abc-cnn-for-visual-question-answering"
    }
  ]
}