資源簡介
深度學習相關代碼實現，可以用來做去噪，去模糊，回歸，識別等
and multinomial inputs (still in development).
Supports binary and noisy rectified linear units (NReLU) in the hidden
代碼片段和文件信息
%%???This?program?trains?Restricted?Boltzmann?Machine：基于CD-1法訓練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m文件運行結束后，得到關于RBM網絡的三部分參數：
%%?RBM網絡訓練結束，得到三組參數：vishid?--?連接權值矩陣，可見層節點數*隱含層節點數
%?????????????????????????????????????????????????????????????????visbiases?--?可見層節點偏置向量?1行*可見層節點數
%??屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件???????7402??2014-03-05?11:10??rbm.m
-----------?---------??----------?-----??----
?????????????????7402????????????????????1
評論
共有 條評論