Skip to main content
. Author manuscript; available in PMC: 2007 Oct 4.
Published in final edited form as: J Speech Lang Hear Res. 1997 Oct;40(5):1085–1096. doi: 10.1044/jslhr.4005.1085

Figure 5.

Figure 5

Buildup of the architecture using cascade correlation for an ANN with four inputs. Inputs are shown on the left (groups are indicated by the Roman numeral and these are detailed fully in Table 2). F, P, and R output units are indicated at the top. Hidden units are added going from the top (no hidden units) to bottom (three hidden units) of the figure as described in the text.