{
  "patent_number": "US 11501192",
  "country": "US",
  "title": "How to Automatically Tune Machine Learning Settings Using Smart Math",
  "original_title": "Systems and methods for Bayesian optimization using non-linear mapping of input",
  "summary": "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.",
  "what_it_does": "This patent describes a way to automate the tuning of machine learning systems, specifically by finding the best hyper-parameters. Hyper-parameters are the configuration settings, like learning rates or layer sizes, that define how a model learns. The system uses a probabilistic model—a mathematical way of representing uncertainty—to predict which settings will yield the best performance. The core innovation is applying a non-linear mapping to these settings before the model processes them, which helps the system better understand complex, non-obvious relationships between settings and outcomes. By iteratively evaluating the system and updating the model, it converges on the optimal configuration.",
  "what_it_does_not_cover": [
    "Does not cover manual tuning of machine learning models by human engineers.",
    "Does not cover optimization methods that rely solely on linear transformations.",
    "Does not cover the actual architecture of the neural network being tuned, only the process of selecting its hyper-parameters.",
    "Does not cover non-probabilistic search methods like simple grid search or random search."
  ],
  "filed": "2018-09-04",
  "granted": "2022-11-15",
  "expires": null,
  "status": "active",
  "holder": "University of Toronto",
  "holder_url": "https://patentbrief.org/company/university-of-toronto",
  "inventors": [
    {
      "name": "Richard Zemel",
      "url": "https://patentbrief.org/inventor/richard-zemel"
    },
    {
      "name": "Kevin Swersky",
      "url": "https://patentbrief.org/inventor/kevin-swersky"
    },
    {
      "name": "Roland Jasper Snoek",
      "url": "https://patentbrief.org/inventor/roland-jasper-snoek"
    },
    {
      "name": "Ryan P. Adams",
      "url": "https://patentbrief.org/inventor/ryan-p-adams"
    }
  ],
  "times_cited": 0,
  "tags": [
    "ai_ml",
    "software",
    "consumer_electronics"
  ],
  "abstract": "Techniques for use in connection with performing optimization using an objective function that maps elements in a first domain to values in a range. The techniques include using at least one computer hardware processor to perform: identifying a first point at which to evaluate the objective function at least in part by using an acquisition utility function and a probabilistic model of the objective function, wherein the probabilistic model depends on a non-linear one-to-one mapping of elements in the first domain to elements in a second domain; evaluating the objective function at the identified first point to obtain a corresponding first value of the objective function; and updating the probabilistic model of the objective function using the first value to obtain an updated probabilistic model of the objective function.",
  "url": "https://patentbrief.org/patent/us/11501192/alphafold-protein-structure-prediction",
  "markdown_url": "https://patentbrief.org/patent/us/11501192/alphafold-protein-structure-prediction/md",
  "google_patents_url": "https://patents.google.com/patent/US11501192",
  "relatedPatents": []
}