Re:What does a neural network actually do?
by tfgg on Monday May 26, 2014 @07:22AM
(#7799336)
You apply a non-linear function (usually some sigmoid) on the output vector after each matrix product. Otherwise, you'd be correct and any multi-layer ANN could be expressed as a single layer network.
[ Parent
| on HN ]
Thanks. It makes sense. The sigmoid is the activation function of the output "neuron". Unfortunately, matrix algebra here is not as useful as in computer graphics.