No abstract

Class Directed Unsupervised Learning (CD UL) [7,8], having an input layer and a fully connected one-dimensional Kohonen layer which is used to conceptually separate data classes. These networks, along with CDUL, have all been developed from the Kohonen Self-Organising Map (SOM) [9,10] and use variations of the associated Kohonen learning rule. In each of these networks, the Kohonen nodes act as exemplars within an adaptive look-up table, and take on values corresponding to the centroids of each distinct data cluster in the feature space. Where CDUL differs is that the input layer is extended to include a class description of each training vector (see Fig. 1), and it is this additional information that provides CDUL with its interesting properties.The reason for the success of CDUL stems from two factors: firstly, the inclusion of class information as an integral section of the input vector, can be used to prevent Kohonen nodes from being trained by vectors of more than one class; and secondly, the size of the Kohonen layer can be computed

A novel neural network called Class Directed Unsupervised Learning (CDUL) is introduced. The architecture, based on a Kohonen self-organising network, uses additional input nodes to feed class knowledge to the network during training, in order to optimise the final positioning of Kohonen nodes in feature space. The structure and training of CDUL networks is detailed, showing that (a) networks cannot suffer from the problem of single Kohonen nodes being trained by vectors of more than one class, (b) the number of Kohonen nodes necessary to represent the classes is found during training, and (c) the number of training set passes CD UL requires is low in comparison to similar networks. CDUL is subsequently applied to the classification of chemical excipients from Near Infrared (NIR) reflectance spectra, and its performance compared with three other unsupervised paradigms. The results thereby obtained demonstrate a superior performance which remains relatively constant through a wide range of network parameters.