Accession Number:

AD0483010

Title:

PATTERN RECOGNITION AND CLASSIFICATION USING ADAPTIVE LINEAR NEURON DEVICES

Descriptive Note:

Master's thesis

Corporate Author:

NAVAL POSTGRADUATE SCHOOL MONTEREY CA

Personal Author(s):

• McGahan, John P.
• Treado, Marshall J.

Report Date:

1964-01-01

Pagination or Media Count:

76.0

Abstract:

Pattern recognition and classification systems have been under development for several years. This paper examines one of these systems, which has been called an adaptive linear neuron, to determine how the desired classification is achieved and how this system might be used in the practical field of character recognition. Specifically, the following ideas are discussed in this paper 1 The basic concepts of linear separability and iterative adaption by an adaptive linear neuron Adaline, as applied to the pattern recognition and classification problem 2 Four possible iterative adaption schemes which may be used to train as Adaline 3 Use of Multiple Adalines Madaline and two logic layers to increase system capability and 4 Use of Adaline in the practical fields of Speech Recognition, Weather Forecasting and Adaptive Control Systems and the possible use of Madaline in the Character Recognition field.

Descriptors:

• *ADAPTIVE SYSTEMS
• ADAPTIVE CONTROL SYSTEMS
• ANALOG SYSTEMS
• CHARACTER RECOGNITION
• CLASSIFICATION
• COMPUTER PROGRAMMING
• DATA PROCESSING
• DIGITAL COMPUTERS
• DIGITAL SYSTEMS
• FLOW CHARTING
• ITERATIONS
• LINEAR SYSTEMS
• MATHEMATICAL MODELS
• MEMORY(PSYCHOLOGY)
• PATTERN RECOGNITION
• SEPARATION
• SPEECH RECOGNITION
• THEORY
• THRESHOLDS(PHYSIOLOGY)
• WEATHER FORECASTING

Subject Categories:

• Bionics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE