Skip to main content
. Author manuscript; available in PMC: 2019 Jul 26.
Published in final edited form as: J Am Stat Assoc. 2018 Jun 28;113(523):955–972. doi: 10.1080/01621459.2017.1409122

Figure 1:

Figure 1:

A fully connected one hidden layer MLP network with three input units (x1, x2, x3), one bias unit (x0), three hidden units (H1, H2, H3), and one output unit (O). The arrows show the direction of data feeding.