Subspace Restricted Boltzmann Machine
This work addresses pattern recognition in machine learning, but appears incremental as it builds on existing Boltzmann machine frameworks.
The paper introduced the subspace Restricted Boltzmann Machine (subspaceRBM), a third-order Boltzmann machine with multiplicative interactions between visible and hidden units, to model pattern variations in data. It was evaluated on the MNIST digit recognition task, showing results in reconstruction and classification errors.
The subspace Restricted Boltzmann Machine (subspaceRBM) is a third-order Boltzmann machine where multiplicative interactions are between one visible and two hidden units. There are two kinds of hidden units, namely, gate units and subspace units. The subspace units reflect variations of a pattern in data and the gate unit is responsible for activating the subspace units. Additionally, the gate unit can be seen as a pooling feature. We evaluate the behavior of subspaceRBM through experiments with MNIST digit recognition task, measuring reconstruction error and classification error.