Skip to main content
. Author manuscript; available in PMC: 2009 Aug 5.
Published in final edited form as: Med Phys. 2007 Sep;34(9):3420–3427. doi: 10.1118/1.2759601

Fig. 1.

Fig. 1

Typical architecture of a three-layer feed-forward neural network. Σ indicates the summation over the bias and weighted inputs (sample weights are indicated above arrows leading between nodes), and σ indicates a linear or nonlinear activation function.