Accession Number:

ADD014663

Title:

Artificial Neural Network Implementation.

Descriptive Note:

Patent, Filed 27 Oct 88, patented 21 Aug 90,

Corporate Author:

DEPARTMENT OF THE NAVY WASHINGTON DC

Personal Author(s):

• Andes, David K.
• Licklider, Robert A.
• Witcher, Donald H.
• Swenson, Richard M.

Report Date:

1990-08-21

Pagination or Media Count:

13.0

Abstract:

An artificial neural network having analog circuits for simultaneous parallel processing using individually variable synaptic input weights. The processing is implemented with a circuit adapted to vary the weight, which may be stored in a metal oxide field effect transistor, for teaching the network or for Hebbian or delta rule learning by the network itself. Keywords Patents, PAT-CL-364-807. Author kr

Descriptors:

• *NEURAL NETS
• *PATENTS
• ANALOG SYSTEMS
• CIRCUITS
• INPUT
• PARALLEL PROCESSING
• SYNAPSE
• SYNCHRONISM
• VARIABLES
• WEIGHT
• FIELD EFFECT TRANSISTORS

Subject Categories:

• Electrical and Electronic Equipment
• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE