Neural network has been used for pattern recognition popularly. The training tlme of neural network for N catalogs classificatlOn mcreases exponentially with N , so it is difficult to deal with large number of catalogs by normal neural networks. Based on binary partition method and decision tree , a binary neural tree network (BNTN) classifier IS proposed. Each node in BNTN is a slmple neural network which only processes 2 catalog classificatlOn. Thus the archi-tecture of BNTN is flexible and expansible , and the training tlme IS reduced largely. The key to construct a BNTN is to sort the classes by separatlOn of each class. We proposed a slmple way to calculate separability of each class after radical basis functlOn (RBF) neural networks have beenselected as a type of node. Simulation shows that BNTN is better than other classifying methods.