Neural Networks: An Overview

Abstract

This report provides an introduction to the field of neural networks, what they are, how they came about, how they work, how they are used, and their current status and potentialities. Neurons are brain cells. There are approximately ten billion (10 to the 10th power) brain cells of varying types in the human brain. These are interconnected by axons and dendrites, the axon being the output fiber of a neuron which branches off into dendrites which in turn connect to other neurons. The interconnectivity can be quite dense with one neuron receiving inputs from up to thousands of others. The action of the neuron is to generate an electrical pulse or pulse train if the summation of its inputs exceeds a threshold associated with a particular neuron. The collection is thus similar to a vast highly interconnected network of threshold elements. It is this network which constitutes the human thinking machine. This thinking machine has capabilities that, to date, have frustrated duplication by large scale digital computers. These capabilities are not in the area of esoteric high level mathematics but in what are generally considered simple normal processes, that is processes that could be performed even by children.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1991
Accession Number
ADA236270

Entities

People

  • Thomas Brady

Organizations

  • United States Army Armament Research, Development and Engineering Center

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Weapons Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence Software
  • Automata Theory
  • Classification
  • Computational Science
  • Computer Science
  • Computer Vision
  • Computers
  • Geometry
  • Image Recognition
  • Network Science
  • Neural Networks
  • Object Recognition
  • Pattern Recognition
  • Psychology
  • Target Recognition

Readers

  • Neural Network Machine Learning.
  • Neuroscience
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks