Engineering of Complex Computer Systems, IEEE International Conference on (1995)
Ft. Lauderdale, Florida
Nov. 6, 1995 to Nov. 10, 1995
M. Kawada , Dept. of Electron. Eng., Hiroshima Univ., Japan
Xu Wu , Dept. of Electron. Eng., Hiroshima Univ., Japan
T. Ae , Dept. of Electron. Eng., Hiroshima Univ., Japan
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.
neural net architecture; real-time systems; case-based reasoning; pattern classification; learning (artificial intelligence); knowledge based systems; algorithm theory; neural-net based AI system construction; neural network technique; real-time neuron-based AI architecture; NAI; real-time case-based reasoning system; winner-take-all type neural network; real-time classification; real-time retrieval; massive case-base; flexible learning; learning algorithms; supervised learning; unsupervised learning; self-organizing learning algorithm; LVQ1 learning algorithm
X. Wu, M. Kawada and T. Ae, "A construction of neural-net based AI systems," Engineering of Complex Computer Systems, IEEE International Conference on(ICECCS), Ft. Lauderdale, Florida, 1995, pp. 424.