Restricted Boltzmann Machine with Multivalued Hidden Variables: a model suppressing over-fitting
This work addresses generalization issues in RBMs, but it is incremental as it extends an existing model with a simple modification.
The authors tackled over-fitting in restricted Boltzmann machines by proposing a model with multivalued hidden variables, demonstrating improved performance over conventional RBMs in numerical experiments on artificial data and MNIST classification.
Generalization is one of the most important issues in machine learning problems. In this study, we consider generalization in restricted Boltzmann machines (RBMs). We propose an RBM with multivalued hidden variables, which is a simple extension of conventional RBMs. We demonstrate that the proposed model is better than the conventional model via numerical experiments for contrastive divergence learning with artificial data and a classification problem with MNIST.