{
  "patent_number": "US 11544573",
  "country": "US",
  "title": "How Projection Neural Networks Speed Up AI Predictions",
  "original_title": "Projection neural networks",
  "summary": "A method for making artificial intelligence models faster and more efficient by using fixed, non-trainable projections to simplify complex data before processing.",
  "what_it_does": "This patent describes a way to build neural networks that are computationally cheaper to run. Instead of training every single part of the network, the system uses 'projection layers' that transform input data into a simpler, lower-dimensional format using fixed parameters that do not change during training. These fixed projections act like a filter, mapping complex inputs to a finite set of values (like 0 or 1) before the rest of the network processes them. By keeping these projection parameters constant, the system reduces the amount of math required to generate a final prediction, making the model faster and less memory-intensive.",
  "what_it_does_not_cover": [
    "Does not cover neural networks where all parameters are updated during the training process.",
    "Does not cover models that do not use a finite set of values (like binary 0 or 1) for the projection function output.",
    "Does not cover systems that lack a projection layer as defined by the specific dot-product and thresholding mechanism described.",
    "Does not cover traditional deep learning architectures that rely solely on standard backpropagation for all layer weights."
  ],
  "filed": "2020-07-13",
  "granted": "2023-01-03",
  "expires": null,
  "status": "active",
  "holder": "Google LLC",
  "holder_url": "https://patentbrief.org/company/google-llc",
  "inventors": [
    {
      "name": "Sujith Ravi",
      "url": "https://patentbrief.org/inventor/sujith-ravi"
    }
  ],
  "times_cited": 1,
  "tags": [
    "ai_ml",
    "consumer_electronics",
    "software"
  ],
  "abstract": "Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a projection neural network. In one aspect, a projection neural network is configured to receive a projection network input and to generate a projection network output from the projection network input. The projection neural network includes a sequence of one or more projection layers. Each projection layer has multiple projection layer parameters, and is configured to receive a layer input, apply multiple projection layer functions to the layer input, and generate a layer output by applying the projection layer parameters for the projection layer to the projection function outputs.",
  "url": "https://patentbrief.org/patent/us/11544573/llama-large-language-model-architecture",
  "markdown_url": "https://patentbrief.org/patent/us/11544573/llama-large-language-model-architecture/md",
  "google_patents_url": "https://patents.google.com/patent/US11544573",
  "relatedPatents": []
}