Daniel@0: Daniel@0: Daniel@0: Daniel@0: Netlab Reference Manual demprior Daniel@0: Daniel@0: Daniel@0: Daniel@0:

demprior Daniel@0:

Daniel@0:

Daniel@0: Purpose Daniel@0:

Daniel@0: Demonstrate sampling from a multi-parameter Gaussian prior. Daniel@0: Daniel@0:

Daniel@0: Synopsis Daniel@0:

Daniel@0: 
Daniel@0: demprior
Daniel@0: Daniel@0: Daniel@0:

Daniel@0: Description Daniel@0:

Daniel@0: This function plots the functions represented by a multi-layer perceptron Daniel@0: network when the weights are set to values drawn from a Gaussian prior Daniel@0: distribution. The parameters aw1, ab1 aw2 and ab2 Daniel@0: control the inverse variances of the first-layer weights, the hidden unit Daniel@0: biases, the second-layer weights and the output unit biases respectively. Daniel@0: Their values can be adjusted on a logarithmic scale using the sliders, or Daniel@0: by typing values into the text boxes and pressing the return key. Daniel@0: Daniel@0:

Daniel@0: See Also Daniel@0:

Daniel@0: mlp
Daniel@0: Pages: Daniel@0: Index Daniel@0:
Daniel@0:

Copyright (c) Ian T Nabney (1996-9) Daniel@0: Daniel@0: Daniel@0: Daniel@0: