Trees | Indices | Help |
---|
|
Example controller which uses a prelearned neural network for controlling the inverted pendulum.
|
|||
NeuroController Neural net controller. |
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|
|||
input_hidden1 = prepareWeightMatrices(([0, 0, 0, 0, 0], [1.352 weights from input layer to hidden layer 1 |
|||
hidden1_hidden2 = prepareWeightMatrices(([0, 0, 0, 0, 0, 0, 0, weights from hidden layer 1 to hidden layer 2 |
|||
hidden2_output = prepareWeightMatrices(([2.6952314,-2.1971807, weights from hidden layer 2 to output layer 2 |
|||
arctanh_0_8 = 1.098612 scaling factor for in-/outputs |
|
multiply vector with matrix. b must be transposed |
multiply two matrices. b must be transposed |
|
input_hidden1weights from input layer to hidden layer 1
|
hidden1_hidden2weights from hidden layer 1 to hidden layer 2
|
hidden2_outputweights from hidden layer 2 to output layer 2
|
Trees | Indices | Help |
---|
Generated by Epydoc 3.0.1 on Tue Sep 22 22:32:07 2009 | http://epydoc.sourceforge.net |