An assential aspect of structured prediction is the evaluation of an output structure against the gold standard. Especially in the loss-augmented setting, the need of finding the max-violating constraint has severely limited the expressivity of effective loss functions. In this paper, we trade off exact computation for enabling the use of more complex loss functions for coreference resolution (...

We apply a new approach to the reverse protein folding problem. Our method uses a minimization function in the design process which is different from the energy function used for folding. For a lattice model, we show that this new approach produces sequences that are likely to fold into desired structures. Our method is a significant improvement over previous attempts which used the energy func...

How can proteins fold so quickly into their unique native structures? We show here that there is a natural analogy between parsing and the protein folding problem, and demonstrate that CKY can find the native structures of a simplified lattice model of proteins with high accuracy.

Massachusetts Institute of Technology 1.

In this paper the author considers an autoregressive process where the parameters of the process are unknown and try to obtain pivots for predicting future observations. If we do a probabilistic prediction with the estimated model, where the parameters are estimated by a sample of size n, we introduce an error of order n−1 in the coverage probabilities of the prediction intervals. However we ca...

in this paper, a novel hybrid model based on neural network and game theory is proposed to support the analyzers in oil market. in this model, first the neural network is utilized to learn the oil prices associated with opec production level and usa imports level. then the learned neural network is applied by a game model. finally the nash equilibrium points of the game present the optimum deci...

Application performance is critical in high-performance computing (HPC), however, it is not considered in a systematic way in the HPC software development process. Integrated performance models could improve this situation. Advanced analytic performance modeling and performance analysis tools exist in isolation but have similar goals and could benefit mutually. We find that existing analysis to...

weather predicts are influence in all aspects of life everyday. more importantly weather warnings are important forecasts because they are used to protect life and property. mesoscale numerical weather prediction models are key for weather forecasting, however the accuracy of the predictions are affected by the errors in the numerical models.study of the clouds is challenging and there are many...

In this work we present a detailed analytical performance model of the large-scale parallel application HYCOM, the Hybrid Coordinate Ocean Model. The performance model is developed from analyzing the activities contained within the code. It is parameterized in terms of both application characteristics (including problem sizes, time-steps, and application phases) and system characteristics (incl...

In intelligent educational systems, assessment of what the learner is doing is a prerequisite for proper, knowledgeable guidance of the educational process. We propose to use existing techniques from the field of modelbased reasoning for this purpose. This paper describes how a modified version of GDF can be exploited in diagnosing a learner’s problem solving behaviour. The problem solving task...