The diffuse self-organizing map

This paper proposes a new diffuse self-organizing map (DSOM), which is a competitive self-organizing neural network that can forms a topological map of the input vector space in a circle-shaped region. Active and inactive neurons are introduced to restrict the range of competition and the size of the final map. Lateral conduction is also introduced to calculate the learning radius and learning rate. DSOM learns in a uniform manner and is capable to learn new classes either within or after its learning stage.