Restricted Boltzmann Machine for Classification with Hierarchical Correlated Prior
This work addresses classification tasks like character recognition and document categorization by improving RBM models with prior knowledge, though it appears incremental as it builds on existing RBM variants.
The paper tackled the problem of classification with Restricted Boltzmann Machines (RBM) by incorporating hierarchical correlated priors to model interclass relationships, showing promising results on challenge datasets compared to competitive baselines.
Restricted Boltzmann machines (RBM) and its variants have become hot research topics recently, and widely applied to many classification problems, such as character recognition and document categorization. Often, classification RBM ignores the interclass relationship or prior knowledge of sharing information among classes. In this paper, we are interested in RBM with the hierarchical prior over classes. We assume parameters for nearby nodes are correlated in the hierarchical tree, and further the parameters at each node of the tree be orthogonal to those at its ancestors. We propose a hierarchical correlated RBM for classification problem, which generalizes the classification RBM with sharing information among different classes. In order to reduce the redundancy between node parameters in the hierarchy, we also introduce orthogonal restrictions to our objective function. We test our method on challenge datasets, and show promising results compared to competitive baselines.