Abstract
This paper presents the spherical classifier, an artificial neural network model for content addressable memory, pattern recognition, and control. The spherical classifier is a high-order dynamical system which stores as memories (attractors) any finite set of unit vectors in n-dimensional space. We illustrate applications of the spherical classifier in classification and control.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have