Feature Extraction using a Hierarchical Growing Neural Gas

Upsupervised, data driven, automatic feature extraction from image data is an interesting and difficult problem. High dimensional data, such as images, often contain less information than they do data. In order for an agent to better reason about this data, finding the interesting features of the data is helpful. A current technique, known as the Growing Neural Gas(GNG), is a neural network approach to feature extraction. There are, however, adaptations that can be made to the Growing Neural Gas in order to increase its performane. Contributions of this work include development of a new neural network algorithm extending the Growing Neural Gas framework, known as the Hierarchical Growing Neural Gas(HGNG), identifications of the parameters of this HGNG which effect feature extraction performance, and a comparison of performance between the normal GNG and the HGNG neural networks