Abstract: ART2 is a kind of self-organizing neural network which is based on adaptive resonance theory.It carries out the classification by using competitive learning and self-steady mechanism，and can learn by itself in dynamic environment with noise and without supervision.Its learning process can recognize learned models fast and be adapted to new unknown objects rapidly.This paper gives out an algorithm of ART2 based on slow weight update rule，which can slow down the learning rate and reduce the speed of pattern drifting in classification for input mode.This paper gets better results in experiment for classification by using the learning rule of new network，and to a certain extent solves the problem of pattern drifting.