wolffd@0: function [y, z, a] = mlpfwd(net, x)
wolffd@0: %MLPFWD	Forward propagation through 2-layer network.
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %	Y = MLPFWD(NET, X) takes a network data structure NET together with a
wolffd@0: %	matrix X of input vectors, and forward propagates the inputs through
wolffd@0: %	the network to generate a matrix Y of output vectors. Each row of X
wolffd@0: %	corresponds to one input vector and each row of Y corresponds to one
wolffd@0: %	output vector.
wolffd@0: %
wolffd@0: %	[Y, Z] = MLPFWD(NET, X) also generates a matrix Z of the hidden unit
wolffd@0: %	activations where each row corresponds to one pattern.
wolffd@0: %
wolffd@0: %	[Y, Z, A] = MLPFWD(NET, X) also returns a matrix A  giving the summed
wolffd@0: %	inputs to each output unit, where each row corresponds to one
wolffd@0: %	pattern.
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	MLP, MLPPAK, MLPUNPAK, MLPERR, MLPBKP, MLPGRAD
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: % Check arguments for consistency
wolffd@0: errstring = consist(net, 'mlp', x);
wolffd@0: if ~isempty(errstring);
wolffd@0:   error(errstring);
wolffd@0: end
wolffd@0: 
wolffd@0: ndata = size(x, 1);
wolffd@0: 
wolffd@0: z = tanh(x*net.w1 + ones(ndata, 1)*net.b1);
wolffd@0: a = z*net.w2 + ones(ndata, 1)*net.b2;
wolffd@0: 
wolffd@0: switch net.outfn
wolffd@0: 
wolffd@0:   case 'linear'    % Linear outputs
wolffd@0: 
wolffd@0:     y = a;
wolffd@0: 
wolffd@0:   case 'logistic'  % Logistic outputs
wolffd@0:     % Prevent overflow and underflow: use same bounds as mlperr
wolffd@0:     % Ensure that log(1-y) is computable: need exp(a) > eps
wolffd@0:     maxcut = -log(eps);
wolffd@0:     % Ensure that log(y) is computable
wolffd@0:     mincut = -log(1/realmin - 1);
wolffd@0:     a = min(a, maxcut);
wolffd@0:     a = max(a, mincut);
wolffd@0:     y = 1./(1 + exp(-a));
wolffd@0: 
wolffd@0:   case 'softmax'   % Softmax outputs
wolffd@0:   
wolffd@0:     % Prevent overflow and underflow: use same bounds as glmerr
wolffd@0:     % Ensure that sum(exp(a), 2) does not overflow
wolffd@0:     maxcut = log(realmax) - log(net.nout);
wolffd@0:     % Ensure that exp(a) > 0
wolffd@0:     mincut = log(realmin);
wolffd@0:     a = min(a, maxcut);
wolffd@0:     a = max(a, mincut);
wolffd@0:     temp = exp(a);
wolffd@0:     y = temp./(sum(temp, 2)*ones(1, net.nout));
wolffd@0: 
wolffd@0:   otherwise
wolffd@0:     error(['Unknown activation function ', net.outfn]);  
wolffd@0: end