Application of Neural Networks with regard to author attribution as a problem of pattern recognition and proven results of their applications make them as promising techniques for the future in continuing authorship determination. Learning Vector Quantization (LVQ) is a neural network technique that develops a codebook of quantization vectors and makes use of these vectors to encode any input vector. In this paper an attempt is made to identify authorship attribute of disputed articles using LVQ and verify with the results obtained by traditional canonical discriminant analysis. This study demonstrates that statistical methods of attributing authorship can be clubbed successfully with neural networks to produce a powerful classification tool. Comparisons are made using means of sixteen articles of syntax identified from thirty - one articles written in Tamil language by three contemporary scholars namely, Mahakavi Bharathiar (MB), Subramaniya Iyer (SI) and T. V. Kalyanasundaranar (TVK) of identical repute to determine the authorship of twenty-three un-attributed articles pertaining to the same period.