A fuzzy classifier based on correlation matrix memories
Eren Aykin, Simon O’Keefe · 2009
This paper describes a binary neural network classifier that is able to make decisions based on fuzzy relational rule sets. Rule sets are extracted from a training data set and stored in a Correlation Matrix Memory (CMM). Such a classifier has many advantages including suitability for hardware implementations, fast matching, handling of missing or erroneous data and online learning. The main purpose of this paper is to demonstrate the suitability of the AURA library for building CMMs that perform fuzzy operations.