{
  "patent_number": "US 12632737",
  "country": "US",
  "title": "How AI Designs Its Own Brains: Hierarchical Neural Architecture Search",
  "original_title": "Using hierarchical representations for neural network architecture searching",
  "summary": "This patent describes a computer method for automatically designing neural networks by representing their structures as multi-level graphs and evolving the best designs based on how well they perform.",
  "what_it_does": "The patent describes a computer-implemented method for automatically finding the best design, or \"architecture,\" for a neural network. It does this by representing a neural network's structure as a \"hierarchical set of graphs\" (Claim 1). Think of these graphs as blueprints with different levels of detail. At the lowest level, the graphs use basic \"primitive neural network operations\" like simple calculations or connections (Claim 1, 2, 3). Higher levels build more complex operations by combining these simpler graphs. The method then creates a group of sample neural network designs, trains them, and measures how well they perform using a \"fitness value\" (Claim 1). It then selects the best-performing designs and can even \"mutate\" them, meaning it makes small changes to create new, potentially better designs, and repeats the process (Claim 8). For example, it might try different combinations of convolutional operations (Claim 3) or even no-connection operations (Claim 5) between nodes to see which arrangement yields the highest fitness.",
  "what_it_does_not_cover": [
    "Does not cover manual design of neural network architectures by human experts.",
    "Does not cover methods for determining architectures that do not use a hierarchical graph representation.",
    "Does not cover methods that evaluate architectures without determining a \"fitness value\" (Claim 1).",
    "Does not cover methods that do not involve \"generating data defining a hierarchical set of graphs\" (Claim 1).",
    "Does not cover methods where the operations for higher-level graphs are not selected from preceding hierarchical levels (Claim 1)."
  ],
  "filed": "2024-01-17",
  "granted": "2026-05-19",
  "expires": "2044-01-17",
  "status": "active",
  "holder": "GDM Holding",
  "holder_url": "https://patentbrief.org/company/gdm-holding",
  "inventors": [
    {
      "name": "Oriol Vinyals",
      "url": "https://patentbrief.org/inventor/oriol-vinyals"
    },
    {
      "name": "Hanxiao Liu",
      "url": "https://patentbrief.org/inventor/hanxiao-liu"
    },
    {
      "name": "Karen Simonyan",
      "url": "https://patentbrief.org/inventor/karen-simonyan"
    },
    {
      "name": "Koray Kavukcuoglu",
      "url": "https://patentbrief.org/inventor/koray-kavukcuoglu"
    },
    {
      "name": "Chrisantha Thomas Fernando",
      "url": "https://patentbrief.org/inventor/chrisantha-thomas-fernando"
    }
  ],
  "times_cited": 0,
  "tags": [
    "ai_ml",
    "software",
    "telecommunications",
    "consumer_electronics"
  ],
  "abstract": "A computer-implemented method for automatically determining a neural network architecture represents a neural network architecture as a data structure defining a hierarchical set of directed acyclic graphs in multiple levels. Each graph has an input, an output, and a plurality of nodes between the input and the output. At each level, a corresponding set of the nodes are connected pairwise by directed edges which indicate operations performed on outputs of one node to generate an input to another node. Each level is associated with a corresponding set of operations. At a lowest level, the operations associated with each edge are selected from a set of primitive operations. The method includes repeatedly generating new sample neural network architectures, and evaluating their fitness. The modification is performed by selecting a level, selecting two nodes at that level, and modifying, removing or adding an edge between those nodes according to operations associated with lower levels of the hierarchy.",
  "url": "https://patentbrief.org/patent/us/12632737/using-hierarchical-representations-for-neural-network-architecture-searching",
  "markdown_url": "https://patentbrief.org/patent/us/12632737/using-hierarchical-representations-for-neural-network-architecture-searching/md",
  "google_patents_url": "https://patents.google.com/patent/US12632737",
  "relatedPatents": [
    {
      "patentNumber": "11501192",
      "countryCode": "US",
      "title": "How to Automatically Tune Machine Learning Settings Using Smart Math",
      "url": "https://patentbrief.org/patent/us/11501192/alphafold-protein-structure-prediction"
    },
    {
      "patentNumber": "20230162023",
      "countryCode": "US",
      "title": "Automated AI for Adapting to New Data Without Retraining",
      "url": "https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement"
    },
    {
      "patentNumber": "10832138",
      "countryCode": "US",
      "title": "How to Automatically Expand Neural Networks by Adding New Nodes",
      "url": "https://patentbrief.org/patent/us/10832138/gpt-language-model-pre-training"
    },
    {
      "patentNumber": "20250371349",
      "countryCode": "US",
      "title": "How AI Learns to Run Faster on Specific Computer Chips",
      "url": "https://patentbrief.org/patent/us/20250371349/methods-and-apparatus-for-hardware-aware-machine-learning-model-training"
    },
    {
      "patentNumber": "11120365",
      "countryCode": "US",
      "title": "How AI Models Learn Complex Tasks by Breaking Them Down",
      "url": "https://patentbrief.org/patent/us/11120365/for-hierarchical-decomposition-deep-reinforcement-learning-for-an-artificial-int"
    }
  ]
}