wolffd@0: function net = mlpinit(net, prior)
wolffd@0: %MLPINIT Initialise the weights in a 2-layer feedforward network.
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %
wolffd@0: %	NET = MLPINIT(NET, PRIOR) takes a 2-layer feedforward network NET and
wolffd@0: %	sets the weights and biases by sampling from a Gaussian distribution.
wolffd@0: %	If PRIOR is a scalar, then all of the parameters (weights and biases)
wolffd@0: %	are sampled from a single isotropic Gaussian with inverse variance
wolffd@0: %	equal to PRIOR. If PRIOR is a data structure of the kind generated by
wolffd@0: %	MLPPRIOR, then the parameters are sampled from multiple Gaussians
wolffd@0: %	according to their groupings (defined by the INDEX field) with
wolffd@0: %	corresponding variances (defined by the ALPHA field).
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	MLP, MLPPRIOR, MLPPAK, MLPUNPAK
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: if isstruct(prior)
wolffd@0:   sig = 1./sqrt(prior.index*prior.alpha);
wolffd@0:   w = sig'.*randn(1, net.nwts); 
wolffd@0: elseif size(prior) == [1 1]
wolffd@0:   w = randn(1, net.nwts).*sqrt(1/prior);
wolffd@0: else
wolffd@0:   error('prior must be a scalar or a structure');
wolffd@0: end  
wolffd@0: 
wolffd@0: net = mlpunpak(net, w);
wolffd@0: