Skip to main content
LeidosPatent grant

Leidos was granted a patent for faster neural-network class learning.

Source: Autobound Signal API · 121 signals tracked for Leidos · updated

Get Leidos' live signals in Claude or ChatGPT, or by API

AskWhat changed at Leidos this week? Use Autobound signals for leidos.com.

What happened

In November 2026 Leidos patented a machine-learning method for rapidly adding recognition categories in near-real-time systems without retaining large historical training datasets.

Source

patents.google.comNov 17, 2026

US patent US12801911

Deep rapid class augmentation

Abstract

Deep RCA uses a modified recursive least squares (RLS) optimization method and a novel null-class vector that together allow the algorithm to remember prior classes as it learns the new class. Deep RCA only has to be trained on the new class data which results in a significant improvement in training speed and almost no memory requirements to achieve the goal of near, real-time class augmentation for deep neural networks.

patents.google.com/patent/US12801911Read the full source

Extracted by Autobound

From the Signal API record
Signal
Patent grant

What this signalsA new patent often shows where a company is putting its R&D budget.

Grant date
Nov 17, 2026
Inventors
Hanna Elizabeth Witzgall
Tech area
artificial intelligence / machine learning
Patent number
US12801911

The full record

From the Signal API record

People

  • Hanna Elizabeth WitzgallInventor

Details

Primary CPC class
G06N 3/08 (Computing arrangements based on specific computational models)
USPTO assignee
Leidos Inc.
What the invention does
A neural-network training approach that learns a new category while preserving earlier categories, using an optimization method and placeholder class representation instead of retraining on everything.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Machine Learning

Technologies named

  • deep neural networks
  • machine learning
  • recursive least squares
  • real-time classification

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Leidos and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Leidos this week?”

  2. Send it to your own tools

    The Signal API returns patent signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full patents-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/15d47e12-5b90-5f34-abc7-c2925dc84348 returns this record as JSON. POST /v1/companies/enrich returns every signal for leidos.com.

{
  "signal_id": "15d47e12-5b90-5f34-abc7-c2925dc84348",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:34:08+00:00",
  "company": {
    "name": "Leidos",
    "domain": "leidos.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06N 3/08",
        "label": "Computing arrangements based on specific computational models"
      },
      {
        "code": "B01L 3/502715"
      },
      {
        "code": "G01N 1/02"
      },
      {
        "code": "G01N 33/5302"
      },
      {
        "code": "G06F 16/55",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning"
    ],
    "detail": "In November 2026 Leidos patented a machine-learning method for rapidly adding recognition categories in near-real-time systems without retaining large historical training datasets.",
    "summary": "Leidos was granted a patent for faster neural-network class learning.",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Hanna Elizabeth Witzgall",
        "status": "resolved",
        "is_primary": true,
        "linkedin_url": "https://www.linkedin.com/in/hanna-witzgall-834068a"
      }
    ],
    "tech_area": "artificial intelligence / machine learning",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12801911",
    "cpc_primary": {
      "code": "G06N 3/08",
      "label": "Computing arrangements based on specific computational models"
    },
    "patent_title": "Deep rapid class augmentation",
    "patent_number": "US12801911",
    "uspto_assignee": "Leidos Inc.",
    "patent_abstract": "Deep RCA uses a modified recursive least squares (RLS) optimization method and a novel null-class vector that together allow the algorithm to remember prior classes as it learns the new class. Deep RCA only has to be trained on the new class data which results in a significant improvement in training speed and almost no memory requirements to achieve the goal of near, real-time class augmentation for deep neural networks.",
    "precision_class": "structural",
    "invention_explanation": "A neural-network training approach that learns a new category while preserving earlier categories, using an optimization method and placeholder class representation instead of retraining on everything.",
    "technologies_mentioned": [
      "deep neural networks",
      "machine learning",
      "recursive least squares",
      "real-time classification"
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.