This paper discusses Kohonen's self-organizing semantic map (SOSM). We
show that augmentation and normalization of numerical feature data as
recommended for the SOSM is entirely unnecessary to obtain semantic m
aps that exhibit semantic similarities between objects represented by
the data, Visual displays of a small data set of 13 animals based on p
rincipal components, Sammon's algorithm, and Kohonen's (unsupervised)
self-organizing feature map (SOFM) possess exactly the same qualitativ
e information as the much more complicated SOSM display does.