Improvement of RBM Based on Label Condition
HE Pengcheng
Abstract：In order to overcome the poor generalization resulted by characteristic homogeneity for unsupervised training of restricted boltzmann machine ,the label condition is introduced to the training of RBM to design a new model named label condition RBM .Training for RBM ,the label information is treated as training condition for RBM and involved in the calcula-tion of hidden units’ posterior probability .The model is applied in deep learning which designed as the underlying structure of deep Boltzmann machine .Through a collection of handwritten numeral recognition test ,the model’s training speed and the effectiveness of feature extraction are greatly improved ,and the characterized learning ability of deep learning model is also improved .
Keywords：restricted Boltzmann machinedeep learningsupervised learningcontrastive divergence
Publication Date：2016-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 1436-1438,1547 )