Skip to main content
Figure 2 | Genetics Selection Evolution

Figure 2

From: Application of neural networks with back-propagation to genome-enabled prediction of complex traits in Holstein-Friesian and German Fleckvieh cattle

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; \(\sum \) indicates some computation.

Back to article page

Genetics Selection Evolution

ISSN: 1297-9686