文档介绍：ARTIFICIAL NEURAL
NETWORKS TECHNOLOGY
A DACS State-of-the-Art Report
Contract Number F30602-89-C-0082
(Data & Analysis Center for Software)
ELIN: A011
August 20 1992
Prepared for:
Rome Laboratory
RL/C3C
Griffiss AFB, NY 13441-5700
Prepared by:
Dave Anderson and e McNeill
Kaman Sciences Corporation
258 Genesse Street
Utica, New York 13502-4627
TABLE OF CONTENTS
Introduction and Purpose ............................................................................. 1
What are Artificial works? ...................................................... 2
Analogy to the Brain ............................................................................. 2
Artificial Neurons and How They Work ......................................... 3
Electronic Implementation of Artificial Neurons.......................... 5
work Operations ............................................................ 7
Training an Artificial work ............................................ 10
Supervised Training.................................................................. 10
Unsupervised, or Adaptive Training.................................... 11
How works Differ from puting
and Expert Systems ............................................................................... 12
History of works......................................................................... 17
Detailed Description of ponents and How
They Work........................................................................................................ 20
ponents of an Artificial Neuron.................................... 22
Teaching an Artificial work............................................ 26
Supervised Learning. ................................................................ 26
Unsupervised Learning............................................................ 27
Learning Rates. .............