Projection on a hypersphere

Of the several approaches that draw upon this general description, radial basis function networks (RBFNs) (Leonard and Kramer, 1991) are probably the best-known. RBFNs are similar in architecture to back propagation networks (BPNs) in that they consist of an input layer, a single hidden layer, and an output layer. The hidden layer makes use of Gaussian basis functions that result in inputs projected on a hypersphere instead of a hyperplane. RBFNs therefore generate spherical clusters in the input data space, as illustrated in Fig. 12. These clusters are generally referred to as receptive fields. 

Input data mapping still corresponds to projection on a hypersphere however, ART uses vector direction to assess similarity rather than using a distance measure as shown in Fig. 15. This translates into the use of hypercone clusters in a unit hypercube. 

---

See also in sourсe #XX -- [ ]

---