PATTERN RECOGNITION AND CLASSIFICATION USING ADAPTIVE LINEAR NEURON DEVICES
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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1964
- Accession Number
- AD0483010
Entities
People
- John P. Mcgahan
- Marshall J. Treado
Organizations
- Naval Postgraduate School