2014/07/16 by Jakub M. Tomczak, Tomczak, Jakub M., Adam Gonczarek +1
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.LG
paper · pdf · doi:10.48550/arxiv.1407.4422
7 pages
arxiv created 2014/07/16 · arxiv updated 2014/07/17
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.