The infinite restricted Boltzmann machine (iRBM) is an extension of the classic RBM. It enjoys a good property of automatically deciding the size of the hidden layer according to specific training data. With sufficient training, the iRBM can achieve a competitive performance with that of the classic RBM. However, the convergence of learning the iRBM is slow, due to the fact that the iRBM is sensitive to the ordering of its hidden units, the learned filters change slowly from the left-most hidden unit to right. To break this dependency between neighboring hidden units and speed up the convergence of training, a novel training strategy is proposed. The key idea of the proposed training strategy is randomly regrouping the hidden units before each gradient descent step. Potentially, a mixing of infinite many iRBMs with different permutations of the hidden units can be achieved by this learning method, which has a similar effect of preventing the model from over-fitting as the dropout. The original iRBM is also modified to be capable of carrying out discriminative training. To evaluate the impact of our method on convergence speed of learning and the model's generalization ability, several experiments have been performed on the binarized MNIST and CalTech101 Silhouettes datasets. Experimental results indicate that the proposed training strategy can greatly accelerate learning and enhance generalization ability of iRBMs.

This choice, which is also related to the finitary and infinitary The model-checking problem for Resource Agent semantics of [Bulling and Farwer, 2010], stipulates whether Logic is known to be undecidable. We review existing in every model, agents always have a choice of doing nothing (un)decidability results and identify a significant (executing an idle action) that produces and consumes fragment of the logic for which model checking no resources [Alechina et al., 2014]. Apart from the technical is decidable. We discuss aspects which makes convenience for model-checking (intuitively it implies model checking decidable and prove undecidability that any strategy to satisfy a next or until formula only needs of two open fragments over a class of models in to ensure the relevant subformula becomes true after finitely which agents always have a choice of doing nothing.