Hardware-based Artificial Neural Networks for Size, Weight, and Power Constrained Platforms (Preprint)

Abstract

A fully parallel, silicon-based artificial neural network (CogniMem CM1K) built on zero instruction set computer technology was used for change detection and object identification in video data. Fundamental pattern recognition capabilities were demonstrated with reduced neuron numbers utilizing only a few, or in some cases one, neuron per category. This simplified approach was used to validate the utility of few neuron networks for use in applications that necessitate severe size, weight, and power restrictions. The limited resource requirements and massively parallel nature of hardware-based artificial neural networks make them superior to many software approaches in resource limited systems, such as micro-UAVs, mobile sensor platforms, and pocket-sized robots.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2012
Accession Number
ADA578194

Entities

People

  • B. T. Wysocki
  • Clare Thiem
  • Nathan McDonald

Organizations

  • Air Force Research Laboratory

Tags

Communities of Interest

  • Advanced Electronics
  • Autonomy
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Application-Specific Integrated Circuits
  • Artificial Intelligence
  • Change Detection
  • Complementary Metal-Oxide Semiconductors
  • Computer Architecture
  • Computers
  • Computing System Architectures
  • Detection
  • Detectors
  • Identification
  • Instruction Set Architecture
  • Machine Learning
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Test And Evaluation

Readers

  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Autonomy