Linear function neurons: Structure and training (Q1070193): Difference between revisions
From MaRDI portal
Revision as of 10:36, 17 June 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Linear function neurons: Structure and training |
scientific article |
Statements
Linear function neurons: Structure and training (English)
0 references
1986
0 references
Three different representations for a thresholded linear equation are developed. For binary input they are shown to be representationally equivalent though their training characteristics differ. A training algorithm for linear equations is discussed. The similarities between its simplest mathematical representation (perceptron training), a formal model of animal learning (Rescorla-Wagner learning), and one mechanism of neural learning (Aplysia gill withdrawal) are pointed out.
0 references
binary input
0 references
training algorithm for linear equations
0 references
perceptron training
0 references
animal learning
0 references
Rescorla-Wagner learning
0 references
neural learning
0 references
Aplysia gill withdrawal
0 references