{
  "patent_number": "US 20250371349",
  "country": "US",
  "title": "How AI Learns to Run Faster on Specific Computer Chips",
  "original_title": "Methods and apparatus for hardware-aware machine learning model training",
  "summary": "This patent describes how a smart AI system, called a reinforcement learning agent, trains other AI models to run more efficiently on specific computer hardware by cleverly reducing their size without losing too much accuracy.",
  "what_it_does": "The patent details a method for optimizing neural networks to run efficiently on a specific hardware device. It uses a \"reinforcement learning agent\" (Claim 1) that receives an \"embedding state\" (Claim 1) representing characteristics of a neural network layer, such as its \"kernel size\" or \"number of weights\" (Claim 4). Based on this information, the agent generates \"actions\" (Claim 1) to reduce the \"computational cycles\" (Claim 1) needed to execute the neural network. A common action is \"pruning weights\" (Claim 2) within the layer, determined by a \"sparsity ratio\" (Claim 2). After the modified neural network runs, the system determines a \"reward\" (Claim 1) for the agent by checking if the output's \"accuracy\" (Claim 1) meets a set threshold and if a \"target cycle reduction\" (Claim 6) was achieved. This reward then helps the agent update its \"policy\" (Claim 1) to make better optimization decisions in the future. For example, an AI model designed to detect objects in a security camera feed could be optimized this way to run quickly on the camera's embedded processor without missing important events.",
  "what_it_does_not_cover": [
    "Optimizing neural networks using methods that do not involve a reinforcement learning agent to generate actions.",
    "Training neural networks without specifically considering the reduction of computational cycles on a target hardware device.",
    "Pruning weights in a neural network without evaluating the impact on both accuracy and computational cycles as part of a reward system.",
    "Optimization techniques that focus solely on improving neural network accuracy without also aiming to reduce execution time.",
    "Manual optimization of neural network layers by a human engineer without an automated learning agent."
  ],
  "filed": "2025-08-21",
  "granted": null,
  "expires": "2045-08-21",
  "status": "active",
  "holder": "Intel",
  "holder_url": "https://patentbrief.org/company/intel",
  "inventors": [
    {
      "name": "Xiaofan Xu",
      "url": "https://patentbrief.org/inventor/xiaofan-xu"
    },
    {
      "name": "Zsolt Biro",
      "url": "https://patentbrief.org/inventor/zsolt-biro"
    },
    {
      "name": "Cormac Brick",
      "url": "https://patentbrief.org/inventor/cormac-brick"
    }
  ],
  "times_cited": 2,
  "tags": [
    "ai_ml",
    "semiconductors",
    "software",
    "consumer_electronics",
    "telecommunications"
  ],
  "abstract": "Methods, apparatus, systems, and articles of manufacture are disclosed for hardware-aware machine learning model training. An example apparatus includes a configuration determiner to determine a hardware configuration of a target hardware platform on which the machine learning model is to be executed, a layer generator to assign sparsity configurations to layers of the machine learning model based on the hardware configuration, and a deployment controller to deploy the machine learning model to the target hardware platform in response to outputs of the machine learning model satisfying respective thresholds, the outputs including a quantity of clock cycles to execute the machine learning model with the layers having the assigned sparsity configurations.",
  "url": "https://patentbrief.org/patent/us/20250371349/methods-and-apparatus-for-hardware-aware-machine-learning-model-training",
  "markdown_url": "https://patentbrief.org/patent/us/20250371349/methods-and-apparatus-for-hardware-aware-machine-learning-model-training/md",
  "google_patents_url": "https://patents.google.com/patent/US20250371349",
  "relatedPatents": [
    {
      "patentNumber": "20250363357",
      "countryCode": "US",
      "title": "How to Update AI on Small Devices with Slow Internet",
      "url": "https://patentbrief.org/patent/us/20250363357/systems-and-methods-for-deploying-and-updating-neural-networks-at-the-edge-of-a-"
    },
    {
      "patentNumber": "11429864",
      "countryCode": "US",
      "title": "Making Neural Networks Faster by Skipping Unnecessary Calculations",
      "url": "https://patentbrief.org/patent/us/11429864/dlss-deep-learning-super-sampling"
    },
    {
      "patentNumber": "20220383078",
      "countryCode": "US",
      "title": "Adapting AI Models to Fit Device Resources",
      "url": "https://patentbrief.org/patent/us/20220383078/data-processing-method-and-related-device"
    },
    {
      "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": "10956815",
      "countryCode": "US",
      "title": "How to Fix Faulty Memory Cells in AI Chips",
      "url": "https://patentbrief.org/patent/us/10956815/killing-asymmetric-resistive-processing-units-for-neural-network-training"
    }
  ]
}