Skip to main content
. 2018 Aug 31;210(3):809–819. doi: 10.1534/genetics.118.301298

Figure 1.

Figure 1

Representation of a Multilayer Perceptron. Each layer is connected to the previous one by a weighted linear summation, here represented by weight matrices W(i), and a (non)linear transformation. Redrawn from http://www.texample.net/tikz/examples/neural-network/.