Perhaps surprisingly, it is possible to predict how long an algorithm will take to run on a previously unseen input, using machine learning techniques to build a model of the algorithm’s runtime as a function of problem-specific instance features. Such models have many important applications and over the past decade, a wide variety of techniques have been studied for building such models. In th...

Animal breeding faces one of the most significant changes of the past decades - the implementation of genomic selection. Genomic selection uses dense marker maps to predict the breeding value of animals with reported accuracies that are up to 0.31 higher than those of pedigree indexes, without the need to phenotype the animals themselves, or close relatives thereof. The basic principle is that ...

Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train. These difficulties come from the fact that optimal weights for adversarial nets correspond to saddle points, and not minimizers, of the loss function. The alternating stochastic gradient methods typically used for such problems do not reliably converge to saddle points, and when co...

Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train. These difficulties come from the fact that optimal weights for adversarial nets correspond to saddle points, and not minimizers, of the loss function. The alternating stochastic gradient methods typically used for such problems do not reliably converge to saddle points, and when co...

Failure prediction methods are becoming sine qua non conditions for effective availability enhancement in complex computer and communication systems. Therefore, there is a growing need for validation, benchmarking and assessment of such methods on real industrial data. Our thesis is that the effectiveness of such methods can be significantly enhanced when combined with fault injection. Then, no...

In this study we compare commonly used coiled-coil prediction methods against a database derived from proteins of known structure. We find that the two older programs COILS and PairCoil/MultiCoil are significantly outperformed by two recent developments: Marcoil, a program built on hidden Markov models, and PCOILS, a new COILS version that uses profiles as inputs; and to a lesser extent by a Pa...

Online Social Networks are growing exponentially due to which a lot of researchers are working on Social Network analysis. Link Prediction is a task of predicting new links that may occur in future in the social network. The link prediction problem has generated a lot of interest due its widespread applicability across many domains. We conducted a study on the different methods that have been d...

In this paper we propose several methods for improving prediction of protein disorder. These include attribute construction from protein sequence, choice of classifier and postprocessing. While ensembles of neural networks achieved the higher accuracy, the difference as compared to logistic regression classifiers was smaller then 1%. Bagging of neural networks, where moving averages over window...