Hierarchical overlapped neural gas network with application to pattern classification

Abstract This paper describes our investigations into the neural gas (NG) network. The original neural gas network is computationally expensive, as an explicit ordering of all distances between synaptic weights and the training sample is necessary. This has a time complexity of O (N log N) in its sequential implementation. An alternative scheme was proposed for the above explicit ordering where it is carried out implicitly. In addition, a truncated weight updating rule was used similar to Choy and Siu (IEEE Trans. Communications 46 (3) (1998) 301–304). By implementing the above modifications, the NG algorithm was made to run faster in its sequential implementation. A hierarchical overlapped neural gas architecture was developed on top of the above modified NG algorithm for the classification of real world handwritten numerals with high variations. This allowed us to obtain multiple classifications for each sample presented, and the final classification was made by fusing the individual classifications. An excellent recognition rate for the NIST SD3 database was consequently obtained.