Modern statistical machine translation (SMT) systems usually use a linear combination of features to model the quality of each translation hypothesis. The linear combination assumes that all the features are in a linear relationship and constrains that each feature interacts with the rest features in an linear manner, which might limit the expressive power of the model and lead to a under-fit m...

The Next Linear Collider (NLC) electron and positron beams are capable of damaging the linac accelerating structure and beamline vacuum chambers during an individual aberrant accelerator pulse. Machine protection system (MPS) considerations, outlined in this paper for the 1 TeV NLC design, have an impact on the engineering and design of most machine components downstream of the damping ring inj...

The ramp loss is a robust but non-convex loss for classification. Compared with other non-convex losses, a local minimum of the ramp loss can be effectively found. The effectiveness of local search comes from the piecewise linearity of the ramp loss. Motivated by the fact that the `1-penalty is piecewise linear as well, the `1-penalty is applied for the ramp loss, resulting in a ramp loss linea...

We present a neural architecture for sequence processing. The ByteNet is a stack of two dilated convolutional neural networks, one to encode the source sequence and one to decode the target sequence, where the target network unfolds dynamically to generate variable length outputs. The ByteNet has two core properties: it runs in time that is linear in the length of the sequences and it preserves...

One-class support vector machine is an important and efficient classifier which is used in the situation that only one class of data is available, and the other is too expensive or difficult to collect. It uses vector as input data, and trains a linear or nonlinear decision function in vector space. However, there is reason to consider data as tensor. Tensor representation can make use of the s...

The Set Covering Machine (SCM) was introduced by Marchand & Shawe–Taylor [6, 7] in which a minimum set cover of a class of examples was approximated to find a compact conjunction/disjunction of features for classification. Their approach was to solve the set cover problem using the greedy algorithm. In this paper we introduce an alternative method of solving the SCM by formulating it as a Linea...

This paper employs an interactive possibility linear programming approach to solve a single machine scheduling problem with imprecise processing times, due dates, as well as earliness and tardiness penalties of jobs. The proposed approach is based on a strategy of minimizing the most possible value of the imprecise total costs, maximizing the possibility of obtaining a lower total costs, and mi...