Abstract: A fast neural classification algorithm named FTART2 is proposed in this paper. It combines the advantages of both adaptive resonance theory and field theory resulting in fast learning speed, strong generality, and high efficiency. FTART2 is tested against the most prevailing neural algorithm BP using two data sets from UCI machine learning repository. Experimental results show that the former is better than the latter in both classification accuracy and learning speed. Moreover, FTART2 has also been applied to the analysis of oil reservoir and satisfactory results have been achieved.