The Cortical Graph (CorGraph) Project - An Investigation Into the Representation of Complex

Abstract

The objective of this effort is to explore neural inspired algorithms, loosely based on cortical structures, as new approaches to capturing and then representing the graphical structure of features in a still or moving image, and then finding the most likely matching subgraph based on probabilistic inference. The approach is to study the use of hierarchical, modular, sparsely distributed structures loosely based on the HTM family of algorithms. There does not seem to be any research in using bioinspired algorithms to solve this problem. And, in fact, only a few people are looking at hierarchical structures based on sparsely distributed representations.

Document Details

Document Type
DoD Grant Award
Publication Date
Apr 25, 2017
Source ID
FA87501710099

Entities

People

  • Dan Hammerstrom

Organizations

  • Portland State University
  • Rome Laboratory
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • Biotechnology