The identification of overrepresented motifs in a collection of biological sequences continues to be a relevant and challenging problem in computational biology. Currently popular methods of motif discovery are based on statistical learning theory. In this paper, a machine-learning approach to the motif discovery problem is explored. The approach is based on a Self-Organizing Map (SOM) where the output layer neuron weight vectors are replaced by position weight matrices. This approach can be used to characterise features present in a set of sequences, and thus can be used as an aid in overrepresented motif discovery. The SOM approach to motif discovery is demonstrated using biological sequence datasets, both real and simulated.