Skip to main content
. 2015 Mar 31;47(1):22. doi: 10.1186/s12711-015-0097-5

Figure 2.

Figure 2

Architecture of a two-layer feed forward neural network. x ij = network input, e.g., marker genotype j of individual i; w 1m = network weight from the input to hidden layer; w 2s = network weight from the hidden to the output layer; y i network output, e.g., predicted phenotype of individual; f(.) = activation function at the hidden neurons; g(.) = activation function at the output neuron; indicates some computation.