We propose a supervised deep learning algorithm based on low-discrepancy sequences as the training set. By combination of theoretical arguments and extensive numerical experiments we demonstrate that proposed significantly outperforms standard algorithms are randomly chosen data for problems in moderately high dimensions. The provides an efficient method building inexpensive surrogates many und...

Classifiers favoring sparse solutions, such as support vector machines, relevance vector machines, LASSO-regression based classifiers, etc., provide competitive methods for classification problems in high dimensions. However, current algorithms for training sparse classifiers typically scale quite unfavorably with respect to the number of training examples. This paper proposes online and multi-...

Memristor-based computer architectures are becoming more attractive as a possible choice of hardware for the implementation neural networks. However, at present, memristor technologies susceptible to variety failure modes, serious concern in any application where regular access may not be expected or even possible. In this study, we investigate whether certain training algorithms resilient part...

Traditional learning to rank methods learn ranking models from training data in a batch and offline learning mode, which suffers from some critical limitations, e.g., poor scalability as the model has to be retrained from scratch whenever new training data arrives. This is clearly nonscalable for many real applications in practice where training data often arrives sequentially and frequently. T...