Extensions of self-organizing feature maps for improved visual displays

This paper addresses the problem of visual assessment of clustering tendency in p-dimensional data using two extensions of Kohonen´s self-organizing feature map (SOFM). We show that SOFM cell displays generally do not produce visual evidence that leads to good guesses about cluster substructure or data density even for 2-dimensional data. The two proposed extensions of SOFM improve the quality of displays and enable us to make better guesses about the existence of substructure in data.