%%???This?program?trains?Restricted?Boltzmann?Machine：基于CD-1法訓(xùn)練RBM模型?
%?in?which?visible?binary?stochastic?pixels?are?connected?to?hidden?binary?stochastic?feature?detectors?
%?using?symmetrically?weighted?connections.?Learning?is?done?with?1-step?Contrastive?Divergence.?

%%??The?program?assumes?that?the?following?variables?are?set?externally:
%?maxepoch??--?maximum?number?of?epochs
%?numhid????--?number?of?hidden?units?
%?batchdata?--?the?data?that?is?divided?into?batches?（numcases?numdims?numbatches）
%?restart???--?set?to?1?if?learning?starts?from?beginning?

%%?20130924??commented?by?ZZH
%%?這個(gè)m文件運(yùn)行結(jié)束后，得到關(guān)于RBM網(wǎng)絡(luò)的三部分參數(shù)：
%%?RBM網(wǎng)絡(luò)訓(xùn)練結(jié)束，得到三組參數(shù)：vishid?--?連接權(quán)值矩陣，可見層節(jié)點(diǎn)數(shù)*隱含層節(jié)點(diǎn)數(shù)
%?????????????????????????????????????????????????????????????????visbiases?--?可見層節(jié)點(diǎn)偏置向量?1行*可見層節(jié)點(diǎn)數(shù)
%?

?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----

?????文件???????7402??2014-03-05?11:10??rbm.m

-----------?---------??----------?-----??----

?????????????????7402????????????????????1