Simple forward example?

[dims12]

How is it possible to create some simple NN, for example, pretrained perceptron with given number of layers and all given weights, and execute it forward?

[ivan-vasilev]

Please take a look at
https://github.com/ivan-vasilev/neuralnetworks/blob/master/nn-samples/src/test/java/com/github/neuralnetworks/samples/test/IrisTest.java
->
testMLPSigmoidBP method, where you can see a 4-2-3 multilayer perceptron
with one hidden layer trained on the IRIS dataset using backpropagation

On Wed, Jun 25, 2014 at 7:10 PM, dims12 notifications@github.com wrote:

How is it possible to create some simple NN, for example, pretrained
perceptron with given number of layers and all given weights, and execute
it forward?

—
Reply to this email directly or view it on GitHub
#30.