Steel+Structure 源代码

function net = mlp(nin, nhidden, nout, outfunc, prior, beta) %MLP Create a 2-layer feedforward network. % % Description % NET = ML…

function net = mdnunpak(net, w) %MDNUNPAK Separates weights vector into weight and bias matrices. % % Description % NET = MDNUNPA…

function errstring = consist(model, type, inputs, outputs) %CONSIST Check that arguments are consistent. % % Description % % ERRST…

function net = mlpinit(net, prior) %MLPINIT Initialise the weights in a 2-layer feedforward network. % % Description % % NET = MLP…

function net = netunpak(net, w) %NETUNPAK Separates weights vector into weight and bias matrices. % % Description % NET = NETUNPA…

function gmmmixes = mdn2gmm(mdnmixes) %MDN2GMM Converts an MDN mixture data structure to array of GMMs. % % Description % GMMMIXES…

function net = glminit(net, prior) %GLMINIT Initialise the weights in a generalized linear model. % % Description % % NET = GLMINI…

function mix = gtmfwd(net) %GTMFWD Forward propagation through GTM. % % Description % MIX = GTMFWD(NET) takes a GTM structure NET…

function net = glm(nin, nout, outfunc, prior, beta) %GLM Create a generalized linear model. % % Description % % NET = GLM(NIN, NOU…

function net = mdn(nin, nhidden, ncentres, dim_target, mix_type, ... prior, beta) %MDN Creates a Mixture Density Network with spe…