Abstract
The paper investigates the integration of the neural network technique and traditional AI techniques towards the realization of a real-time neuron-based AI architecture. As the first step of our project, we propose a neural network based AI system, called NAI. NAI is a kind of real-time CBR (case-based reasoning) system in which the WTA (winner-take-all) type neural network is embedded for supporting the real-time classification and retrieval of a massive case-base. For flexible learning with the WTA neural network, two learning algorithms (supervised and unsupervised) have been developed on the basis of the LVQ1 and self-organizing learning algorithms.