Fuzzy associative memory architecture

Abstract

Artificial neural networks (ANNs) are systems that are deliberately constructed to make use of some organizational principles resembling those in the human brain. ANNs have a large number of highly interconnected processing elements (perceptrons) that usually operate in parallel and are configured in regular architectures. The collective behavior of an ANN, like a human brain, demonstrates the ability to learn, recall, and generalize from training patterns or data. They are good at tasks such as classification, function approximation, optimization, and data clustering [1]. The cerebellar model articulation controller (CMAC), a perceptron-like associative memory equipped with overlapping receptive field proposed by Albus [2], belongs to a special category of ANNs. It was first applied in the domain of control problems. During the past decades, its ability to capture nonlinear function has been demonstrated through many applications in control, function approximation and pattern recognition.