Search

Artificial Intelligence (AI) as an independent discipline has been conceived in the early fifties. Meanwhile, it has become a melting pot of diverse techniques aiming at research on and simulation of the human way of thinking. Originally, the field of AI could be considered an offspring of cognition science, but recently the application-oriented aspect has prevailed. AI has brought us, among many new concepts, a host of long-established techniques, veiled in a new terminology. The question is: Can these new techniques be applied to real-time problems?

Recently, neural networks have evolved as an alternate approach instead of rule-based systems for data compression and automated solution of interpolation or classification problems. The most prominent feature of the neural processing paradigm is its inherent adaptability permitting fairly easy modification of a neural system to perform in a wide range of application environments. This paper presents the cosine classifier, a neural network model designed for unsupervised adaptation and solution of classification problems. Classification of hand-written digits is used to demonstrate its performance.