Data Driven Discovery Of Models

Abstract

D3M aims to develop automated model discovery systems that enable users with subject matter expertise but no data science background to create empirical models of real, complex processes. BBN focused on one aspect of the automation problem: Developing selectable primitives for time-series pattern discovery. BBN developed prototype primitives that are discoverable by other D3M performers who aim to automatically compose primitives into a model building pipe-line.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 30, 2021
Accession Number
AD1130251

Entities

People

  • Prasanna Muthukumar

Organizations

  • RTX

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Artificial Intelligence Software
  • Contracts
  • Cross Domain
  • Data Science
  • Employment
  • Government Procurement
  • Governments
  • Information Exchange
  • Instructions
  • Machine Learning
  • Military Research
  • Models
  • Neural Networks
  • Personnel Management
  • Pipelines
  • Prototypes
  • Security
  • Standards
  • Technical Information Centers

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Instructional Design and Training Evaluation.
  • Software Engineering.

Technology Areas

  • AI & ML