world-information.org

 CONTENTS   SEARCH   HISTORY   HELP 



   

 WORLD-INFOSTRUCTURE > SLAVE AND EXPERT SYSTEMS
  1. Introduction: The Substitution of Human Faculties with Technology: Early Tools
  2. Introduction: The Substitution of Human Faculties with Technology: Powered Machines
  3. Introduction: The Substitution of Human Faculties with Technology: Computers and Robots
  4. Introduction: The Substitution of Human Faculties with Technology: Artificial Intelligence and Expert Systems
  5. Early Tools and Machines
  6. The 17th Century: The Invention of the First "Computers"
  7. The 18th Century: Powered Machines and the Industrial Revolution
  8. The 19th Century: Machine-Assisted Manufacturing
  9. The 19th Century: First Programmable Computing Devices
  10. 1913: Henry Ford and the Assembly Line
  11. 1940s - Early 1950s: First Generation Computers
  12. 1950: The Turing Test
  13. 1940s - 1950s: The Development of Early Robotics Technology
  14. 1950s: The Beginnings of Artificial Intelligence (AI) Research
  15. Late 1950s - Early 1960s: Second Generation Computers
  16. 1961: Installation of the First Industrial Robot
  17. Late 1960s - Early 1970s: Third Generation Computers
  18. 1960s - 1970s: Increased Research in Artificial Intelligence (AI)
  19. 1960s - 1970s: Expert Systems Gain Attendance
  20. 1970s: Computer-Integrated Manufacturing (CIM)
  21. Late 1970s - Present: Fourth Generation Computers
  22. 1980s: Artificial Intelligence (AI) - From Lab to Life
 INDEX CARD     RESEARCH MATRIX 
Neural network
A bottom-up artificial intelligence approach, a neural network is a network of many very simple processors ("units" or "neurons"), each possibly having a (small amount of) local memory. The units are connected by unidirectional communication channels ("connections"), which carry numeric data. The units operate only on their local data and on the inputs they receive via the connections. A neural network is a processing device, either an algorithm, or actual hardware, whose design was inspired by the design and functioning of animal brains and components thereof. Most neural networks have some sort of "training" rule whereby the weights of connections are adjusted on the basis of presented patterns. In other words, neural networks "learn" from examples and exhibit some structural capability for generalization.